Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1482 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.4264. Min Act: -0.1700
Data Index: 8208190 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.3009. Min Act: -0.1700
Data Index: 1767977 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2538. Min Act: -0.1700
Data Index: 6151256 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2852. Min Act: -0.1700
Data Index: 2573394 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2852. Min Act: -0.1700
Data Index: 8342291 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2381. Min Act: -0.1700
Data Index: 2849287 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2538. Min Act: -0.1700
Data Index: 3294360 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2538. Min Act: -0.1700
Data Index: 7869403 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2538. Min Act: -0.1700
Data Index: 3992430 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2381. Min Act: -0.1700
Data Index: 940902 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2538. Min Act: -0.1700
Data Index: 6921627 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2381. Min Act: -0.1700
Data Index: 5881102 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2223. Min Act: -0.1700
Data Index: 4038169 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2223. Min Act: -0.1700
Data Index: 2285508 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2223. Min Act: -0.1700
Data Index: 1748801 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2066. Min Act: -0.1700
Data Index: 8580146 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2223. Min Act: -0.1700
Data Index: 249580 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2066. Min Act: -0.1700
Data Index: 496665 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2066. Min Act: -0.1700
Data Index: 2382231 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4264. Min Range: -3.4264
Max Act: 3.2066. Min Act: -0.1700
Data Index: 690159 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19