Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 685 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.5649. Min Act: -0.1697
Data Index: 4255778 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.5562. Min Act: -0.1700
Data Index: 7379255 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.5386. Min Act: -0.1700
Data Index: 4553764 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.5211. Min Act: -0.1700
Data Index: 1616459 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.5211. Min Act: -0.1700
Data Index: 8535026 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.5123. Min Act: -0.1700
Data Index: 2514782 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.5123. Min Act: -0.1700
Data Index: 2416278 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.5123. Min Act: -0.1699
Data Index: 932396 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.4948. Min Act: -0.1700
Data Index: 6662958 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.5036. Min Act: -0.1700
Data Index: 3427089 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.4772. Min Act: -0.1693
Data Index: 4535534 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.4772. Min Act: -0.1699
Data Index: 8093012 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.4860. Min Act: -0.1700
Data Index: 7536379 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.4772. Min Act: -0.1693
Data Index: 8769470 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.4860. Min Act: -0.1700
Data Index: 3240725 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.4860. Min Act: -0.1700
Data Index: 3359804 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.4860. Min Act: -0.1700
Data Index: 3049953 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.4772. Min Act: -0.1691
Data Index: 3109978 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.4684. Min Act: -0.1652
Data Index: 1940779 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5649. Min Range: -1.5649
Max Act: 1.4772. Min Act: -0.1700
Data Index: 7295424 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19