Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1898 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.5280. Min Act: -0.1700
Data Index: 2219700 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.3093. Min Act: -0.1700
Data Index: 7487109 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.2780. Min Act: -0.1700
Data Index: 835478 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.2155. Min Act: -0.1700
Data Index: 8189492 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.1842. Min Act: -0.1700
Data Index: 6491338 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.1842. Min Act: -0.1700
Data Index: 8701385 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.1217. Min Act: -0.1700
Data Index: 6167491 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.1217. Min Act: -0.1700
Data Index: 6650805 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.1217. Min Act: -0.1700
Data Index: 8317723 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.1217. Min Act: -0.1700
Data Index: 7194058 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.1217. Min Act: -0.1700
Data Index: 7067601 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.1217. Min Act: -0.1700
Data Index: 4741982 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.1217. Min Act: -0.1700
Data Index: 3161275 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.0905. Min Act: -0.1700
Data Index: 1208156 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.0905. Min Act: -0.1700
Data Index: 2919425 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.0905. Min Act: -0.1700
Data Index: 3700711 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.0905. Min Act: -0.1700
Data Index: 6634851 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.0592. Min Act: -0.1700
Data Index: 1685128 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.0280. Min Act: -0.1700
Data Index: 6579719 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5280. Min Range: -4.5280
Max Act: 4.0592. Min Act: -0.1700
Data Index: 3943214 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19