Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4449 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.8049. Min Act: -0.1700
Data Index: 8083981 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.6487. Min Act: -0.1700
Data Index: 6656791 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.6487. Min Act: -0.1700
Data Index: 4768313 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.5862. Min Act: -0.1700
Data Index: 2803454 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.6174. Min Act: -0.1700
Data Index: 4565600 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.5237. Min Act: -0.1700
Data Index: 996265 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.4924. Min Act: -0.1700
Data Index: 6307464 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.4299. Min Act: -0.1700
Data Index: 2594274 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.3987. Min Act: -0.1700
Data Index: 3854267 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.3987. Min Act: -0.1700
Data Index: 1362377 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.3674. Min Act: -0.1700
Data Index: 4915389 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.3674. Min Act: -0.1700
Data Index: 6709325 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.3674. Min Act: -0.1700
Data Index: 2045517 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.3362. Min Act: -0.1700
Data Index: 6873684 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.3049. Min Act: -0.1700
Data Index: 1897299 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.2737. Min Act: -0.1700
Data Index: 5564627 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.2737. Min Act: -0.1700
Data Index: 6838951 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.2424. Min Act: -0.1700
Data Index: 2476978 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.2424. Min Act: -0.1700
Data Index: 177998 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.2112. Min Act: -0.1700
Data Index: 7489382 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19