Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.6163. Min Act: -0.1700
Data Index: 7919902 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.5538. Min Act: -0.1700
Data Index: 2402200 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.5538. Min Act: -0.1700
Data Index: 2302530 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.4601. Min Act: -0.1700
Data Index: 4169689 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.4601. Min Act: -0.1700
Data Index: 8304192 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.1788. Min Act: -0.1700
Data Index: 5291182 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.1476. Min Act: -0.1700
Data Index: 3514799 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.1476. Min Act: -0.1700
Data Index: 1249468 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.1163. Min Act: -0.1700
Data Index: 1155138 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6163. Min Range: -6.6163
Max Act: 5.9913. Min Act: -0.1700
Data Index: 4509293 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6163. Min Range: -6.6163
Max Act: 5.9913. Min Act: -0.1700
Data Index: 693742 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.0226. Min Act: -0.1700
Data Index: 819488 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6163. Min Range: -6.6163
Max Act: 5.9913. Min Act: -0.1700
Data Index: 5230582 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6163. Min Range: -6.6163
Max Act: 5.9601. Min Act: -0.1700
Data Index: 621944 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6163. Min Range: -6.6163
Max Act: 5.9288. Min Act: -0.1700
Data Index: 6131400 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6163. Min Range: -6.6163
Max Act: 5.9288. Min Act: -0.1700
Data Index: 6957234 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6163. Min Range: -6.6163
Max Act: 5.9288. Min Act: -0.1700
Data Index: 8266572 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6163. Min Range: -6.6163
Max Act: 5.8976. Min Act: -0.1700
Data Index: 5389788 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6163. Min Range: -6.6163
Max Act: 5.8663. Min Act: -0.1700
Data Index: 7039999 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6163. Min Range: -6.6163
Max Act: 5.8663. Min Act: -0.1700
Data Index: 7410390 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19