Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1140. Min Range: -2.1140
Max Act: 2.1140. Min Act: -0.1700
Data Index: 5618651 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1140. Min Range: -2.1140
Max Act: 2.0805. Min Act: -0.1700
Data Index: 1918002 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1140. Min Range: -2.1140
Max Act: 2.0805. Min Act: -0.1700
Data Index: 5440794 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1140. Min Range: -2.1140
Max Act: 2.0637. Min Act: -0.1700
Data Index: 7984421 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1140. Min Range: -2.1140
Max Act: 2.0469. Min Act: -0.1700
Data Index: 3649105 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1140. Min Range: -2.1140
Max Act: 2.0301. Min Act: -0.1700
Data Index: 7561525 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1140. Min Range: -2.1140
Max Act: 2.0132. Min Act: -0.1700
Data Index: 5195185 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1140. Min Range: -2.1140
Max Act: 2.0469. Min Act: -0.1700
Data Index: 4708592 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1140. Min Range: -2.1140
Max Act: 2.0301. Min Act: -0.1700
Data Index: 4156155 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1140. Min Range: -2.1140
Max Act: 2.0301. Min Act: -0.1700
Data Index: 1726022 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1140. Min Range: -2.1140
Max Act: 1.9963. Min Act: -0.1700
Data Index: 492230 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1140. Min Range: -2.1140
Max Act: 1.9963. Min Act: -0.1700
Data Index: 4358749 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1140. Min Range: -2.1140
Max Act: 2.0132. Min Act: -0.1700
Data Index: 341821 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1140. Min Range: -2.1140
Max Act: 1.9963. Min Act: -0.1700
Data Index: 3829574 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1140. Min Range: -2.1140
Max Act: 1.9963. Min Act: -0.1700
Data Index: 8412450 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1140. Min Range: -2.1140
Max Act: 1.9963. Min Act: -0.1700
Data Index: 6684245 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1140. Min Range: -2.1140
Max Act: 1.9963. Min Act: -0.1700
Data Index: 3468240 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1140. Min Range: -2.1140
Max Act: 1.9963. Min Act: -0.1700
Data Index: 472025 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1140. Min Range: -2.1140
Max Act: 1.9794. Min Act: -0.1700
Data Index: 5964578 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1140. Min Range: -2.1140
Max Act: 1.9624. Min Act: -0.1700
Data Index: 1667382 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19