Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 500 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.4443. Min Act: -0.1700
Data Index: 3864838 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.4443. Min Act: -0.1700
Data Index: 8011313 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.4130. Min Act: -0.1700
Data Index: 1315872 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.3818. Min Act: -0.1700
Data Index: 5976364 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.3818. Min Act: -0.1700
Data Index: 6282882 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.3505. Min Act: -0.1700
Data Index: 810405 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.3193. Min Act: -0.1700
Data Index: 8724850 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.2880. Min Act: -0.1700
Data Index: 3810730 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.2880. Min Act: -0.1700
Data Index: 1888856 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.2568. Min Act: -0.1700
Data Index: 2427914 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.2568. Min Act: -0.1700
Data Index: 2626284 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.2568. Min Act: -0.1700
Data Index: 2709093 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.2255. Min Act: -0.1700
Data Index: 7940755 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.1943. Min Act: -0.1700
Data Index: 1154495 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.1943. Min Act: -0.1700
Data Index: 4431878 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.1943. Min Act: -0.1700
Data Index: 8047766 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.1943. Min Act: -0.1700
Data Index: 6689894 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.1943. Min Act: -0.1700
Data Index: 5604841 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.1630. Min Act: -0.1700
Data Index: 4422941 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4443. Min Range: -5.4443
Max Act: 5.1318. Min Act: -0.1700
Data Index: 4088650 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19