Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4707 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.5361. Min Act: -0.1700
Data Index: 6758173 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.5049. Min Act: -0.1700
Data Index: 6758179 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.5049. Min Act: -0.1700
Data Index: 4251558 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.4736. Min Act: -0.1700
Data Index: 1713191 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.4111. Min Act: -0.1700
Data Index: 7714216 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.3486. Min Act: -0.1700
Data Index: 3993431 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.3174. Min Act: -0.1700
Data Index: 431516 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.3174. Min Act: -0.1700
Data Index: 6300487 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.3174. Min Act: -0.1700
Data Index: 1656487 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.2861. Min Act: -0.1700
Data Index: 5697141 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.2549. Min Act: -0.1700
Data Index: 6758183 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.2549. Min Act: -0.1700
Data Index: 6889204 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.2549. Min Act: -0.1700
Data Index: 2170950 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.2549. Min Act: -0.1700
Data Index: 1882127 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.2236. Min Act: -0.1700
Data Index: 6758178 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.2236. Min Act: -0.1700
Data Index: 8521720 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.2236. Min Act: -0.1700
Data Index: 5850440 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.2236. Min Act: -0.1700
Data Index: 6331965 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.1924. Min Act: -0.1700
Data Index: 6758172 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5361. Min Range: -5.5361
Max Act: 5.1924. Min Act: -0.1700
Data Index: 4251557 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19