Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3978 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.9416. Min Act: -0.1700
Data Index: 6097502 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.8791. Min Act: -0.1700
Data Index: 8005292 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.8791. Min Act: -0.1700
Data Index: 7838082 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.6291. Min Act: -0.1700
Data Index: 1595724 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.6291. Min Act: -0.1700
Data Index: 7340912 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.5666. Min Act: -0.1700
Data Index: 1852051 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.5666. Min Act: -0.1700
Data Index: 2228070 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.4416. Min Act: -0.1700
Data Index: 5943922 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.4416. Min Act: -0.1700
Data Index: 8555742 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.3791. Min Act: -0.1700
Data Index: 329568 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.3166. Min Act: -0.1700
Data Index: 7175820 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.2541. Min Act: -0.1700
Data Index: 1381775 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.2541. Min Act: -0.1700
Data Index: 5892319 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.1916. Min Act: -0.1700
Data Index: 3320349 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.1916. Min Act: -0.1700
Data Index: 6822602 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.2541. Min Act: -0.1700
Data Index: 1161404 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.1916. Min Act: -0.1700
Data Index: 6549871 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.1291. Min Act: -0.1700
Data Index: 6655713 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.1291. Min Act: -0.1700
Data Index: 1079433 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9416. Min Range: -8.9416
Max Act: 8.1291. Min Act: -0.1700
Data Index: 148670 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19