Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1383 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.7224. Min Act: -0.1700
Data Index: 44801 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.5974. Min Act: -0.1700
Data Index: 44800 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.4724. Min Act: -0.1700
Data Index: 258695 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.4724. Min Act: -0.1700
Data Index: 4445877 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.3474. Min Act: -0.1700
Data Index: 6371748 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.3786. Min Act: -0.1700
Data Index: 7247382 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.3161. Min Act: -0.1700
Data Index: 1476062 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.3474. Min Act: -0.1700
Data Index: 239848 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.1911. Min Act: -0.1700
Data Index: 6058884 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.1911. Min Act: -0.1700
Data Index: 2700650 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.1286. Min Act: -0.1700
Data Index: 503637 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.1286. Min Act: -0.1700
Data Index: 7215836 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.0974. Min Act: -0.1700
Data Index: 4221144 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.1286. Min Act: -0.1700
Data Index: 3762607 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.1286. Min Act: -0.1700
Data Index: 199236 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.0974. Min Act: -0.1700
Data Index: 1069335 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.1286. Min Act: -0.1700
Data Index: 3494766 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.0974. Min Act: -0.1700
Data Index: 2645319 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.0661. Min Act: -0.1700
Data Index: 260576 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7224. Min Range: -4.7224
Max Act: 4.0974. Min Act: -0.1700
Data Index: 3762611 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19