Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 827 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.5367. Min Act: -0.1700
Data Index: 1187299 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.4740. Min Act: -0.1700
Data Index: 3581037 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.4740. Min Act: -0.1700
Data Index: 7955319 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.4740. Min Act: -0.1700
Data Index: 5654943 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.4270. Min Act: -0.1700
Data Index: 3911275 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.4270. Min Act: -0.1700
Data Index: 2721092 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.4114. Min Act: -0.1700
Data Index: 7010858 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.3486. Min Act: -0.1700
Data Index: 809781 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.3329. Min Act: -0.1700
Data Index: 3988258 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.3800. Min Act: -0.1700
Data Index: 3837122 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.3486. Min Act: -0.1700
Data Index: 4920269 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.3486. Min Act: -0.1700
Data Index: 5396771 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.3172. Min Act: -0.1700
Data Index: 3475452 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.3172. Min Act: -0.1700
Data Index: 7364234 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.2859. Min Act: -0.1700
Data Index: 4965163 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.3172. Min Act: -0.1700
Data Index: 3130057 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.3172. Min Act: -0.1700
Data Index: 3581034 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.3016. Min Act: -0.1700
Data Index: 6659022 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.3172. Min Act: -0.1700
Data Index: 6119868 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5367. Min Range: -3.5367
Max Act: 3.3016. Min Act: -0.1700
Data Index: 2922152 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19