Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2469 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.2274. Min Act: -0.1700
Data Index: 5556284 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.2117. Min Act: -0.1700
Data Index: 6296453 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.1960. Min Act: -0.1700
Data Index: 3262167 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.1645. Min Act: -0.1700
Data Index: 5381808 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.1488. Min Act: -0.1699
Data Index: 6296449 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.1173. Min Act: -0.1700
Data Index: 3806392 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.1015. Min Act: -0.1700
Data Index: 7315747 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.1015. Min Act: -0.1700
Data Index: 3049708 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.0858. Min Act: -0.1700
Data Index: 6861454 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.0542. Min Act: -0.1700
Data Index: 7695148 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.0858. Min Act: -0.1700
Data Index: 3850279 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.0858. Min Act: -0.1700
Data Index: 65632 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.1015. Min Act: -0.1700
Data Index: 4806583 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.0700. Min Act: -0.1700
Data Index: 3049706 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.0700. Min Act: -0.1700
Data Index: 6660296 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.0858. Min Act: -0.1700
Data Index: 3200034 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.0700. Min Act: -0.1698
Data Index: 5885882 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.0542. Min Act: -0.1700
Data Index: 3327440 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.0542. Min Act: -0.1699
Data Index: 6217843 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2274. Min Range: -3.2274
Max Act: 3.0384. Min Act: -0.1700
Data Index: 3104290 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19