Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3999 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1503. Min Range: -5.1503
Max Act: 5.1503. Min Act: -0.1700
Data Index: 5096694 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1503. Min Range: -5.1503
Max Act: 5.1191. Min Act: -0.1700
Data Index: 6357252 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1503. Min Range: -5.1503
Max Act: 5.0878. Min Act: -0.1700
Data Index: 430980 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1503. Min Range: -5.1503
Max Act: 5.0878. Min Act: -0.1700
Data Index: 4016198 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1503. Min Range: -5.1503
Max Act: 5.0566. Min Act: -0.1700
Data Index: 334275 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1503. Min Range: -5.1503
Max Act: 4.9941. Min Act: -0.1700
Data Index: 8131758 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1503. Min Range: -5.1503
Max Act: 5.0253. Min Act: -0.1700
Data Index: 5923778 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1503. Min Range: -5.1503
Max Act: 5.0253. Min Act: -0.1700
Data Index: 4832986 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1503. Min Range: -5.1503
Max Act: 4.9941. Min Act: -0.1700
Data Index: 4727364 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1503. Min Range: -5.1503
Max Act: 4.9941. Min Act: -0.1700
Data Index: 4141117 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1503. Min Range: -5.1503
Max Act: 5.0253. Min Act: -0.1700
Data Index: 6762129 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1503. Min Range: -5.1503
Max Act: 4.9941. Min Act: -0.1700
Data Index: 1674551 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1503. Min Range: -5.1503
Max Act: 4.9941. Min Act: -0.1700
Data Index: 4676687 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1503. Min Range: -5.1503
Max Act: 4.9628. Min Act: -0.1700
Data Index: 6278683 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1503. Min Range: -5.1503
Max Act: 4.9628. Min Act: -0.1700
Data Index: 7832847 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1503. Min Range: -5.1503
Max Act: 4.9628. Min Act: -0.1700
Data Index: 4968359 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1503. Min Range: -5.1503
Max Act: 4.9628. Min Act: -0.1700
Data Index: 5688688 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1503. Min Range: -5.1503
Max Act: 4.9628. Min Act: -0.1700
Data Index: 4601271 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1503. Min Range: -5.1503
Max Act: 4.9628. Min Act: -0.1700
Data Index: 8340567 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1503. Min Range: -5.1503
Max Act: 4.9316. Min Act: -0.1700
Data Index: 1324867 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19