Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1578 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.8530. Min Act: -0.1700
Data Index: 4290120 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.7905. Min Act: -0.1700
Data Index: 5407500 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.7905. Min Act: -0.1700
Data Index: 8754509 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.7280. Min Act: -0.1700
Data Index: 1448664 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.7280. Min Act: -0.1700
Data Index: 3803496 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.7280. Min Act: -0.1700
Data Index: 1428240 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.7280. Min Act: -0.1700
Data Index: 584473 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.6655. Min Act: -0.1700
Data Index: 849047 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.6655. Min Act: -0.1700
Data Index: 7606727 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.6030. Min Act: -0.1700
Data Index: 3768884 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.6655. Min Act: -0.1700
Data Index: 2636154 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.5405. Min Act: -0.1700
Data Index: 2300362 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.5405. Min Act: -0.1700
Data Index: 1420331 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.5405. Min Act: -0.1700
Data Index: 6386965 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.4780. Min Act: -0.1699
Data Index: 7321373 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.4780. Min Act: -0.1700
Data Index: 5764465 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.4780. Min Act: -0.1700
Data Index: 2814544 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.4780. Min Act: -0.1700
Data Index: 4625557 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.4780. Min Act: -0.1700
Data Index: 5256020 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8530. Min Range: -10.8530
Max Act: 10.4155. Min Act: -0.1700
Data Index: 3603595 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19