Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3994 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.5949. Min Act: -0.1700
Data Index: 5846534 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.5324. Min Act: -0.1700
Data Index: 1629271 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.4074. Min Act: -0.1700
Data Index: 2948141 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.3449. Min Act: -0.1700
Data Index: 4694289 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.4074. Min Act: -0.1700
Data Index: 2774683 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.3449. Min Act: -0.1700
Data Index: 6852122 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.3449. Min Act: -0.1700
Data Index: 5326720 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.3136. Min Act: -0.1700
Data Index: 5305482 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.2824. Min Act: -0.1700
Data Index: 7569924 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.2824. Min Act: -0.1700
Data Index: 49199 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.2511. Min Act: -0.1700
Data Index: 1062129 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.2199. Min Act: -0.1700
Data Index: 7073607 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.2199. Min Act: -0.1700
Data Index: 7727439 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.2199. Min Act: -0.1700
Data Index: 8055530 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.2199. Min Act: -0.1700
Data Index: 2962152 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.1886. Min Act: -0.1700
Data Index: 3754597 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.1574. Min Act: -0.1700
Data Index: 7313592 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.1886. Min Act: -0.1700
Data Index: 5675889 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.1886. Min Act: -0.1700
Data Index: 7370652 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5949. Min Range: -5.5949
Max Act: 5.1886. Min Act: -0.1700
Data Index: 5438860 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19