Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2468 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.4278. Min Act: -0.1700
Data Index: 1021388 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.3298. Min Act: -0.1700
Data Index: 7700118 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.3298. Min Act: -0.1700
Data Index: 6003722 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.3133. Min Act: -0.1700
Data Index: 5049419 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.2969. Min Act: -0.1700
Data Index: 4871368 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.2804. Min Act: -0.1700
Data Index: 4650339 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.2969. Min Act: -0.1700
Data Index: 4790664 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.2639. Min Act: -0.1700
Data Index: 4767853 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.2309. Min Act: -0.1700
Data Index: 4052850 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.2474. Min Act: -0.1700
Data Index: 3806023 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.2474. Min Act: -0.1700
Data Index: 1195923 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.2309. Min Act: -0.1700
Data Index: 3325852 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.2309. Min Act: -0.1700
Data Index: 6720033 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.2309. Min Act: -0.1700
Data Index: 3899291 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.1977. Min Act: -0.1700
Data Index: 8655758 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.1977. Min Act: -0.1700
Data Index: 5511792 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.2143. Min Act: -0.1700
Data Index: 3493100 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.2143. Min Act: -0.1700
Data Index: 2473624 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.2143. Min Act: -0.1700
Data Index: 7375225 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4278. Min Range: -2.4278
Max Act: 2.1977. Min Act: -0.1700
Data Index: 4005122 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19