Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2361 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.5735. Min Range: -13.5735
Max Act: 13.5735. Min Act: -0.1700
Data Index: 2488489 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.5735. Min Range: -13.5735
Max Act: 13.3235. Min Act: -0.1700
Data Index: 1087809 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.8860. Min Act: -0.1700
Data Index: 1049112 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.8235. Min Act: -0.1700
Data Index: 5069161 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.7610. Min Act: -0.1700
Data Index: 8150017 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.7610. Min Act: -0.1700
Data Index: 7087377 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.6360. Min Act: -0.1700
Data Index: 8025451 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.5735. Min Act: -0.1700
Data Index: 6895174 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.5110. Min Act: -0.1700
Data Index: 8811312 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.5110. Min Act: -0.1700
Data Index: 1087808 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.5110. Min Act: -0.1700
Data Index: 5743138 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.4485. Min Act: -0.1700
Data Index: 2018775 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.3860. Min Act: -0.1700
Data Index: 694800 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.3235. Min Act: -0.1700
Data Index: 4302211 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.2610. Min Act: -0.1700
Data Index: 2608377 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.1985. Min Act: -0.1700
Data Index: 8025452 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.1985. Min Act: -0.1700
Data Index: 2065081 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.1360. Min Act: -0.1700
Data Index: 2699678 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.1360. Min Act: -0.1700
Data Index: 878149 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.5735. Min Range: -13.5735
Max Act: 12.1360. Min Act: -0.1700
Data Index: 2124807 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19