Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3236 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.6134. Min Act: -0.1700
Data Index: 4792648 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.4884. Min Act: -0.1700
Data Index: 4379464 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.5509. Min Act: -0.1700
Data Index: 1510531 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.4884. Min Act: -0.1700
Data Index: 3814463 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.3634. Min Act: -0.1700
Data Index: 6237285 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.3634. Min Act: -0.1700
Data Index: 2204315 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.3634. Min Act: -0.1700
Data Index: 8568510 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.3634. Min Act: -0.1700
Data Index: 364496 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.3634. Min Act: -0.1700
Data Index: 1504759 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.3009. Min Act: -0.1700
Data Index: 2912225 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.2384. Min Act: -0.1700
Data Index: 4505335 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.3009. Min Act: -0.1700
Data Index: 3125482 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.3009. Min Act: -0.1700
Data Index: 2547752 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.3009. Min Act: -0.1700
Data Index: 3555781 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.3009. Min Act: -0.1700
Data Index: 3181093 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.3009. Min Act: -0.1700
Data Index: 8417303 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.2384. Min Act: -0.1700
Data Index: 3185514 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.2384. Min Act: -0.1700
Data Index: 8506282 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.2384. Min Act: -0.1700
Data Index: 6069276 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6134. Min Range: -9.6134
Max Act: 9.2384. Min Act: -0.1700
Data Index: 617307 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19