Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3005. Min Range: -9.3005
Max Act: 9.3005. Min Act: -0.1700
Data Index: 6023479 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3005. Min Range: -9.3005
Max Act: 9.2380. Min Act: -0.1700
Data Index: 5293641 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3005. Min Range: -9.3005
Max Act: 9.1130. Min Act: -0.1700
Data Index: 1023215 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3005. Min Range: -9.3005
Max Act: 9.0505. Min Act: -0.1700
Data Index: 5418681 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.9880. Min Act: -0.1700
Data Index: 1246593 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.8630. Min Act: -0.1700
Data Index: 4857484 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.8005. Min Act: -0.1700
Data Index: 5126831 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.7380. Min Act: -0.1700
Data Index: 8146589 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.6755. Min Act: -0.1700
Data Index: 5293414 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.6130. Min Act: -0.1700
Data Index: 4366782 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.4880. Min Act: -0.1700
Data Index: 1480500 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.4255. Min Act: -0.1700
Data Index: 3040470 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.4255. Min Act: -0.1699
Data Index: 4055905 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.4255. Min Act: -0.1700
Data Index: 5647491 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.4255. Min Act: -0.1700
Data Index: 8735876 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.4255. Min Act: -0.1700
Data Index: 100433 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.4255. Min Act: -0.1700
Data Index: 8016954 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.4255. Min Act: -0.1700
Data Index: 7466617 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.4255. Min Act: -0.1700
Data Index: 4315723 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3005. Min Range: -9.3005
Max Act: 8.3630. Min Act: -0.1700
Data Index: 6883059 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19