Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3014 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.7993. Min Act: -0.1700
Data Index: 877707 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.7993. Min Act: -0.1700
Data Index: 2096571 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.7368. Min Act: -0.1700
Data Index: 1815796 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.6118. Min Act: -0.1700
Data Index: 637459 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.5493. Min Act: -0.1700
Data Index: 1331515 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.5493. Min Act: -0.1700
Data Index: 7314812 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.5493. Min Act: -0.1700
Data Index: 416123 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.5493. Min Act: -0.1700
Data Index: 1699250 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.4243. Min Act: -0.1700
Data Index: 6251233 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.3931. Min Act: -0.1700
Data Index: 5530177 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.4243. Min Act: -0.1700
Data Index: 573365 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.3931. Min Act: -0.1700
Data Index: 2328344 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.3931. Min Act: -0.1700
Data Index: 8123268 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.3931. Min Act: -0.1700
Data Index: 2149301 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.3931. Min Act: -0.1700
Data Index: 7931102 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.3618. Min Act: -0.1700
Data Index: 8434467 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.3931. Min Act: -0.1700
Data Index: 8747296 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.3618. Min Act: -0.1700
Data Index: 8814887 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.3306. Min Act: -0.1700
Data Index: 3513038 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7993. Min Range: -7.7993
Max Act: 7.3306. Min Act: -0.1700
Data Index: 1030117 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19