Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3830 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.7756. Min Act: -0.1700
Data Index: 5949587 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.7131. Min Act: -0.1700
Data Index: 3159026 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.6506. Min Act: -0.1700
Data Index: 5650200 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.6506. Min Act: -0.1700
Data Index: 6009278 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.6194. Min Act: -0.1700
Data Index: 8087897 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.5881. Min Act: -0.1700
Data Index: 2821329 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.5881. Min Act: -0.1700
Data Index: 5266705 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.5569. Min Act: -0.1700
Data Index: 1352286 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.4631. Min Act: -0.1700
Data Index: 2523251 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.4944. Min Act: -0.1700
Data Index: 5953737 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.4631. Min Act: -0.1700
Data Index: 4479715 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.4631. Min Act: -0.1700
Data Index: 1624154 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.4631. Min Act: -0.1700
Data Index: 4850316 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.4319. Min Act: -0.1700
Data Index: 7781596 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.4319. Min Act: -0.1700
Data Index: 2140728 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.4319. Min Act: -0.1700
Data Index: 2704924 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.4319. Min Act: -0.1700
Data Index: 3621761 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.4319. Min Act: -0.1700
Data Index: 6094380 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.3694. Min Act: -0.1700
Data Index: 5471902 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7756. Min Range: -5.7756
Max Act: 5.3381. Min Act: -0.1700
Data Index: 1141654 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19