Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4059 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5735. Min Range: -6.5735
Max Act: 6.5735. Min Act: -0.1700
Data Index: 2949480 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.8235. Min Act: -0.1700
Data Index: 555832 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.8547. Min Act: -0.1700
Data Index: 7798455 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.7297. Min Act: -0.1700
Data Index: 4397663 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.6985. Min Act: -0.1700
Data Index: 5426210 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.6985. Min Act: -0.1700
Data Index: 850804 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.6047. Min Act: -0.1700
Data Index: 5892509 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.5735. Min Act: -0.1700
Data Index: 2162522 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.5735. Min Act: -0.1700
Data Index: 8499260 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.5422. Min Act: -0.1700
Data Index: 6593744 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.5422. Min Act: -0.1700
Data Index: 6372161 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.5110. Min Act: -0.1700
Data Index: 3390605 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.5110. Min Act: -0.1700
Data Index: 8391590 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.4797. Min Act: -0.1700
Data Index: 4027125 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.5110. Min Act: -0.1700
Data Index: 7336323 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.4172. Min Act: -0.1700
Data Index: 125535 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.4172. Min Act: -0.1700
Data Index: 2754428 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.4172. Min Act: -0.1700
Data Index: 7781712 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.4172. Min Act: -0.1700
Data Index: 3393693 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5735. Min Range: -6.5735
Max Act: 5.3547. Min Act: -0.1700
Data Index: 7564260 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19