Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5703 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3424. Min Range: -9.3424
Max Act: 9.2799. Min Act: -0.1700
Data Index: 3502273 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3424. Min Range: -9.3424
Max Act: 9.3424. Min Act: -0.1700
Data Index: 2091917 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3424. Min Range: -9.3424
Max Act: 9.2799. Min Act: -0.1700
Data Index: 4440924 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3424. Min Range: -9.3424
Max Act: 9.2174. Min Act: -0.1700
Data Index: 4502042 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3424. Min Range: -9.3424
Max Act: 9.1549. Min Act: -0.1700
Data Index: 4259785 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3424. Min Range: -9.3424
Max Act: 9.0924. Min Act: -0.1700
Data Index: 5594108 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3424. Min Range: -9.3424
Max Act: 9.0299. Min Act: -0.1700
Data Index: 5288207 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3424. Min Range: -9.3424
Max Act: 8.9674. Min Act: -0.1700
Data Index: 1609107 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3424. Min Range: -9.3424
Max Act: 8.9674. Min Act: -0.1700
Data Index: 5609152 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3424. Min Range: -9.3424
Max Act: 8.9049. Min Act: -0.1700
Data Index: 2979049 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3424. Min Range: -9.3424
Max Act: 8.7799. Min Act: -0.1700
Data Index: 111592 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3424. Min Range: -9.3424
Max Act: 8.7799. Min Act: -0.1700
Data Index: 3274462 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3424. Min Range: -9.3424
Max Act: 8.8424. Min Act: -0.1700
Data Index: 294501 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3424. Min Range: -9.3424
Max Act: 8.6549. Min Act: -0.1700
Data Index: 7591750 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3424. Min Range: -9.3424
Max Act: 8.7174. Min Act: -0.1700
Data Index: 1406410 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3424. Min Range: -9.3424
Max Act: 8.7174. Min Act: -0.1700
Data Index: 4610154 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3424. Min Range: -9.3424
Max Act: 8.7174. Min Act: -0.1700
Data Index: 690538 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3424. Min Range: -9.3424
Max Act: 8.7174. Min Act: -0.1700
Data Index: 8079038 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3424. Min Range: -9.3424
Max Act: 8.7174. Min Act: -0.1700
Data Index: 3245449 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3424. Min Range: -9.3424
Max Act: 8.7174. Min Act: -0.1700
Data Index: 2087709 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19