Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3613. Min Range: -6.3613
Max Act: 6.3613. Min Act: -0.1700
Data Index: 267684 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3613. Min Range: -6.3613
Max Act: 6.3300. Min Act: -0.1700
Data Index: 478423 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3613. Min Range: -6.3613
Max Act: 6.2988. Min Act: -0.1700
Data Index: 7885454 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3613. Min Range: -6.3613
Max Act: 6.2675. Min Act: -0.1700
Data Index: 5595734 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3613. Min Range: -6.3613
Max Act: 6.2363. Min Act: -0.1700
Data Index: 5437242 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3613. Min Range: -6.3613
Max Act: 6.2050. Min Act: -0.1700
Data Index: 8684489 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3613. Min Range: -6.3613
Max Act: 6.1113. Min Act: -0.1700
Data Index: 2766273 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3613. Min Range: -6.3613
Max Act: 6.0488. Min Act: -0.1700
Data Index: 3883654 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3613. Min Range: -6.3613
Max Act: 6.0175. Min Act: -0.1700
Data Index: 7659219 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3613. Min Range: -6.3613
Max Act: 6.0175. Min Act: -0.1700
Data Index: 8676056 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3613. Min Range: -6.3613
Max Act: 5.9863. Min Act: -0.1700
Data Index: 8564103 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3613. Min Range: -6.3613
Max Act: 5.9863. Min Act: -0.1700
Data Index: 2261860 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3613. Min Range: -6.3613
Max Act: 5.9550. Min Act: -0.1700
Data Index: 3141153 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3613. Min Range: -6.3613
Max Act: 5.9238. Min Act: -0.1700
Data Index: 1484429 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3613. Min Range: -6.3613
Max Act: 5.9238. Min Act: -0.1700
Data Index: 4361901 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3613. Min Range: -6.3613
Max Act: 5.8925. Min Act: -0.1700
Data Index: 5959535 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3613. Min Range: -6.3613
Max Act: 5.9238. Min Act: -0.1700
Data Index: 3447525 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3613. Min Range: -6.3613
Max Act: 5.8613. Min Act: -0.1700
Data Index: 2867634 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3613. Min Range: -6.3613
Max Act: 5.8613. Min Act: -0.1700
Data Index: 6769839 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3613. Min Range: -6.3613
Max Act: 5.8613. Min Act: -0.1700
Data Index: 1942518 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19