Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3123 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.6450. Min Act: -0.1700
Data Index: 8676772 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.4887. Min Act: -0.1700
Data Index: 5426218 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.4575. Min Act: -0.1700
Data Index: 4928606 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.4262. Min Act: -0.1700
Data Index: 5426221 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.4262. Min Act: -0.1700
Data Index: 1946557 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.3950. Min Act: -0.1700
Data Index: 4203773 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.3950. Min Act: -0.1700
Data Index: 5843118 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.3950. Min Act: -0.1700
Data Index: 5775888 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.3325. Min Act: -0.1700
Data Index: 7221049 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.3325. Min Act: -0.1700
Data Index: 7905974 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.3325. Min Act: -0.1700
Data Index: 980514 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.3012. Min Act: -0.1700
Data Index: 2117778 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.3012. Min Act: -0.1700
Data Index: 3711592 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.3012. Min Act: -0.1700
Data Index: 6614050 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.3012. Min Act: -0.1700
Data Index: 3948169 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.3012. Min Act: -0.1700
Data Index: 5917706 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.2700. Min Act: -0.1700
Data Index: 4979406 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.2700. Min Act: -0.1700
Data Index: 7449677 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.2700. Min Act: -0.1700
Data Index: 6476931 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6450. Min Range: -6.6450
Max Act: 6.2700. Min Act: -0.1700
Data Index: 8160863 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19