Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2539 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.9250. Min Act: -0.1700
Data Index: 4718798 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.8615. Min Act: -0.1700
Data Index: 6185866 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.8457. Min Act: -0.1700
Data Index: 5873363 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7979. Min Act: -0.1700
Data Index: 1539586 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7820. Min Act: -0.1700
Data Index: 6186543 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7820. Min Act: -0.1700
Data Index: 233410 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7820. Min Act: -0.1700
Data Index: 5914504 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7661. Min Act: -0.1700
Data Index: 566759 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7661. Min Act: -0.1700
Data Index: 5592885 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7501. Min Act: -0.1700
Data Index: 8275497 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7820. Min Act: -0.1700
Data Index: 1844882 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7341. Min Act: -0.1700
Data Index: 5748248 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7341. Min Act: -0.1700
Data Index: 2519805 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7181. Min Act: -0.1700
Data Index: 7173986 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7181. Min Act: -0.1700
Data Index: 6485711 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7181. Min Act: -0.1700
Data Index: 4246312 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7181. Min Act: -0.1700
Data Index: 5914503 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7181. Min Act: -0.1700
Data Index: 8668610 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.7022. Min Act: -0.1700
Data Index: 513973 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9250. Min Range: -2.9250
Max Act: 2.6861. Min Act: -0.1700
Data Index: 2924427 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19