Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.6505. Min Act: -0.1700
Data Index: 1983025 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.4943. Min Act: -0.1700
Data Index: 8368769 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.4630. Min Act: -0.1700
Data Index: 8533916 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.4005. Min Act: -0.1700
Data Index: 508500 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.3693. Min Act: -0.1700
Data Index: 6895108 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.3380. Min Act: -0.1700
Data Index: 8799237 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.3068. Min Act: -0.1700
Data Index: 780166 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.2755. Min Act: -0.1700
Data Index: 6811919 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.2443. Min Act: -0.1700
Data Index: 188356 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.2443. Min Act: -0.1700
Data Index: 4917348 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.2443. Min Act: -0.1700
Data Index: 3026343 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.2443. Min Act: -0.1700
Data Index: 6918800 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.2443. Min Act: -0.1700
Data Index: 1237648 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.1818. Min Act: -0.1700
Data Index: 8473018 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.1818. Min Act: -0.1700
Data Index: 888676 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.1505. Min Act: -0.1700
Data Index: 5530386 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.1818. Min Act: -0.1700
Data Index: 4706748 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.1505. Min Act: -0.1700
Data Index: 7212989 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.1505. Min Act: -0.1700
Data Index: 5831013 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6505. Min Range: -4.6505
Max Act: 4.1505. Min Act: -0.1700
Data Index: 1210363 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19