Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1098 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.4264. Min Act: -0.1700
Data Index: 5225432 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.3951. Min Act: -0.1700
Data Index: 5009486 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.3639. Min Act: -0.1700
Data Index: 8409205 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.3326. Min Act: -0.1700
Data Index: 8788907 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.2389. Min Act: -0.1700
Data Index: 4467061 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.2389. Min Act: -0.1700
Data Index: 6641607 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.2389. Min Act: -0.1700
Data Index: 4554530 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.2076. Min Act: -0.1700
Data Index: 6536514 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.1763. Min Act: -0.1700
Data Index: 7071006 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.1763. Min Act: -0.1700
Data Index: 6334861 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.1763. Min Act: -0.1700
Data Index: 6182243 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.2076. Min Act: -0.1700
Data Index: 1058211 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.1451. Min Act: -0.1700
Data Index: 6509145 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.1451. Min Act: -0.1700
Data Index: 6042676 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.1138. Min Act: -0.1700
Data Index: 1750120 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.0826. Min Act: -0.1700
Data Index: 2314333 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.1138. Min Act: -0.1700
Data Index: 4485579 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.1138. Min Act: -0.1700
Data Index: 6193129 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.0513. Min Act: -0.1700
Data Index: 3063478 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.1138. Min Act: -0.1700
Data Index: 5111754 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19