Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3373 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7355. Min Range: -7.7355
Max Act: 7.7355. Min Act: -0.1700
Data Index: 7347329 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7355. Min Range: -7.7355
Max Act: 7.3292. Min Act: -0.1700
Data Index: 3123470 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7355. Min Range: -7.7355
Max Act: 7.2042. Min Act: -0.1700
Data Index: 7693792 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7355. Min Range: -7.7355
Max Act: 7.1105. Min Act: -0.1700
Data Index: 885010 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.9855. Min Act: -0.1700
Data Index: 7515083 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.9230. Min Act: -0.1700
Data Index: 2712677 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.8605. Min Act: -0.1700
Data Index: 4826476 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.8605. Min Act: -0.1700
Data Index: 1495687 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.8292. Min Act: -0.1700
Data Index: 5447904 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.8292. Min Act: -0.1700
Data Index: 5532766 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.8292. Min Act: -0.1700
Data Index: 1357464 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.7980. Min Act: -0.1700
Data Index: 8325256 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.7980. Min Act: -0.1700
Data Index: 3394580 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.7667. Min Act: -0.1700
Data Index: 1306777 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.7980. Min Act: -0.1700
Data Index: 5598841 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.7667. Min Act: -0.1700
Data Index: 8348581 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.7667. Min Act: -0.1700
Data Index: 2453437 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.7355. Min Act: -0.1700
Data Index: 2007925 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.7042. Min Act: -0.1700
Data Index: 5876944 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7355. Min Range: -7.7355
Max Act: 6.7355. Min Act: -0.1700
Data Index: 790877 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19