Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3320 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.7763. Min Act: -0.1700
Data Index: 3411911 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.6513. Min Act: -0.1700
Data Index: 7944986 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.6200. Min Act: -0.1700
Data Index: 3506812 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.5575. Min Act: -0.1700
Data Index: 4545943 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.5263. Min Act: -0.1700
Data Index: 5907343 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.5263. Min Act: -0.1700
Data Index: 3447914 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.5263. Min Act: -0.1700
Data Index: 130296 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.4950. Min Act: -0.1700
Data Index: 7231852 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.4325. Min Act: -0.1700
Data Index: 3707812 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.4013. Min Act: -0.1700
Data Index: 30920 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.4325. Min Act: -0.1700
Data Index: 1637235 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.4325. Min Act: -0.1700
Data Index: 7521699 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.4325. Min Act: -0.1700
Data Index: 4475970 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.4325. Min Act: -0.1700
Data Index: 6692365 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.4013. Min Act: -0.1700
Data Index: 3619522 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.4013. Min Act: -0.1700
Data Index: 8702342 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.4013. Min Act: -0.1700
Data Index: 3631400 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.4013. Min Act: -0.1700
Data Index: 6952377 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.3700. Min Act: -0.1700
Data Index: 6206242 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7763. Min Range: -4.7763
Max Act: 4.3388. Min Act: -0.1700
Data Index: 4358292 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19