Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3222 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.5521. Min Act: -0.1700
Data Index: 2290987 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.4896. Min Act: -0.1700
Data Index: 1463857 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.4584. Min Act: -0.1700
Data Index: 3499150 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.4271. Min Act: -0.1700
Data Index: 4615322 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.3959. Min Act: -0.1700
Data Index: 2699532 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.3959. Min Act: -0.1700
Data Index: 3935408 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.3646. Min Act: -0.1700
Data Index: 5289364 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.3334. Min Act: -0.1700
Data Index: 6305277 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.3021. Min Act: -0.1700
Data Index: 163517 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.3021. Min Act: -0.1700
Data Index: 5910451 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.3021. Min Act: -0.1700
Data Index: 2699544 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.2709. Min Act: -0.1700
Data Index: 158531 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.2709. Min Act: -0.1700
Data Index: 5718967 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.2396. Min Act: -0.1700
Data Index: 7981135 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.2396. Min Act: -0.1700
Data Index: 1463856 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.2084. Min Act: -0.1700
Data Index: 6878861 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.2084. Min Act: -0.1700
Data Index: 3211117 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.1771. Min Act: -0.1700
Data Index: 7305608 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.1771. Min Act: -0.1700
Data Index: 2699541 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5521. Min Range: -4.5521
Max Act: 4.1459. Min Act: -0.1700
Data Index: 7193670 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19