Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.7969. Min Act: -0.1700
Data Index: 8024680 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.7031. Min Act: -0.1700
Data Index: 1695998 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.6719. Min Act: -0.1700
Data Index: 7052099 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.6406. Min Act: -0.1700
Data Index: 8370233 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.6094. Min Act: -0.1700
Data Index: 1311674 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.5469. Min Act: -0.1700
Data Index: 2586277 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.5781. Min Act: -0.1700
Data Index: 5376575 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.5156. Min Act: -0.1700
Data Index: 8672223 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.4844. Min Act: -0.1700
Data Index: 7720945 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.4219. Min Act: -0.1700
Data Index: 1939214 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.4219. Min Act: -0.1700
Data Index: 3092158 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.4531. Min Act: -0.1700
Data Index: 1532723 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.4219. Min Act: -0.1700
Data Index: 1884039 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.4219. Min Act: -0.1700
Data Index: 2590634 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.4219. Min Act: -0.1700
Data Index: 7975856 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.4219. Min Act: -0.1700
Data Index: 4400933 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.3594. Min Act: -0.1700
Data Index: 7690164 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.3594. Min Act: -0.1700
Data Index: 8245334 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.3281. Min Act: -0.1700
Data Index: 7344736 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7969. Min Range: -6.7969
Max Act: 6.3281. Min Act: -0.1700
Data Index: 2413499 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19