Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1252 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.4549. Min Act: -0.1700
Data Index: 5529341 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.4393. Min Act: -0.1700
Data Index: 8040631 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.3766. Min Act: -0.1700
Data Index: 2419958 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.3295. Min Act: -0.1700
Data Index: 6290823 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2981. Min Act: -0.1700
Data Index: 2837348 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.3138. Min Act: -0.1700
Data Index: 1914422 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2981. Min Act: -0.1700
Data Index: 5905574 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2824. Min Act: -0.1700
Data Index: 5968847 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2667. Min Act: -0.1700
Data Index: 5453589 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2510. Min Act: -0.1700
Data Index: 4296492 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2510. Min Act: -0.1700
Data Index: 428636 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2667. Min Act: -0.1700
Data Index: 4766149 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2353. Min Act: -0.1700
Data Index: 2768851 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2196. Min Act: -0.1700
Data Index: 2743952 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2038. Min Act: -0.1700
Data Index: 7041273 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2196. Min Act: -0.1700
Data Index: 2378572 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2038. Min Act: -0.1700
Data Index: 7385936 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2196. Min Act: -0.1700
Data Index: 3907410 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2353. Min Act: -0.1700
Data Index: 413932 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4549. Min Range: -3.4549
Max Act: 3.2038. Min Act: -0.1700
Data Index: 7801448 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19