Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5518 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.6161. Min Act: -0.1700
Data Index: 50022 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.6161. Min Act: -0.1700
Data Index: 6363241 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.5355. Min Act: -0.1700
Data Index: 18397 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.5355. Min Act: -0.1700
Data Index: 4331161 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.5193. Min Act: -0.1700
Data Index: 2988117 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.5193. Min Act: -0.1700
Data Index: 8136906 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.5031. Min Act: -0.1700
Data Index: 5820101 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.4869. Min Act: -0.1700
Data Index: 3775473 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.4869. Min Act: -0.1700
Data Index: 5955178 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.4869. Min Act: -0.1700
Data Index: 8039074 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.4869. Min Act: -0.1700
Data Index: 7634160 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.4869. Min Act: -0.1700
Data Index: 5537514 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.4707. Min Act: -0.1700
Data Index: 6104347 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.4544. Min Act: -0.1700
Data Index: 2803377 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.4869. Min Act: -0.1700
Data Index: 2036903 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.4707. Min Act: -0.1700
Data Index: 6077487 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.4707. Min Act: -0.1700
Data Index: 4749639 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.4707. Min Act: -0.1700
Data Index: 3255014 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.4707. Min Act: -0.1700
Data Index: 8777126 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6161. Min Range: -2.6161
Max Act: 2.4707. Min Act: -0.1700
Data Index: 2323058 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19