Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3543 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4865. Min Range: -4.4865
Max Act: 4.4865. Min Act: -0.1700
Data Index: 6716375 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4865. Min Range: -4.4865
Max Act: 4.3302. Min Act: -0.1700
Data Index: 4253212 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4865. Min Range: -4.4865
Max Act: 4.1115. Min Act: -0.1700
Data Index: 3017236 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4865. Min Range: -4.4865
Max Act: 4.1427. Min Act: -0.1700
Data Index: 7366404 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4865. Min Range: -4.4865
Max Act: 4.1115. Min Act: -0.1700
Data Index: 4827648 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4865. Min Range: -4.4865
Max Act: 4.1115. Min Act: -0.1700
Data Index: 7482312 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4865. Min Range: -4.4865
Max Act: 4.0802. Min Act: -0.1700
Data Index: 7554371 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4865. Min Range: -4.4865
Max Act: 4.0802. Min Act: -0.1700
Data Index: 4701781 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4865. Min Range: -4.4865
Max Act: 4.0802. Min Act: -0.1700
Data Index: 3142659 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4865. Min Range: -4.4865
Max Act: 4.0489. Min Act: -0.1700
Data Index: 1779780 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4865. Min Range: -4.4865
Max Act: 4.0177. Min Act: -0.1700
Data Index: 5034783 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4865. Min Range: -4.4865
Max Act: 4.0489. Min Act: -0.1700
Data Index: 1746214 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4865. Min Range: -4.4865
Max Act: 3.9864. Min Act: -0.1700
Data Index: 1631089 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4865. Min Range: -4.4865
Max Act: 3.9864. Min Act: -0.1700
Data Index: 2325864 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4865. Min Range: -4.4865
Max Act: 3.9552. Min Act: -0.1700
Data Index: 1898064 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4865. Min Range: -4.4865
Max Act: 3.9552. Min Act: -0.1700
Data Index: 3397838 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4865. Min Range: -4.4865
Max Act: 3.9552. Min Act: -0.1700
Data Index: 5796579 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4865. Min Range: -4.4865
Max Act: 3.9552. Min Act: -0.1700
Data Index: 1232616 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4865. Min Range: -4.4865
Max Act: 3.9552. Min Act: -0.1700
Data Index: 2234257 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4865. Min Range: -4.4865
Max Act: 3.9552. Min Act: -0.1700
Data Index: 1566316 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19