Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9572. Min Range: -10.9572
Max Act: 10.9572. Min Act: -0.1700
Data Index: 8659304 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9572. Min Range: -10.9572
Max Act: 10.5197. Min Act: -0.1700
Data Index: 2619020 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9572. Min Range: -10.9572
Max Act: 10.3947. Min Act: -0.1700
Data Index: 4774101 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9572. Min Range: -10.9572
Max Act: 10.3947. Min Act: -0.1700
Data Index: 7569084 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9572. Min Range: -10.9572
Max Act: 10.2697. Min Act: -0.1700
Data Index: 696552 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9572. Min Range: -10.9572
Max Act: 10.2697. Min Act: -0.1700
Data Index: 8130729 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9572. Min Range: -10.9572
Max Act: 10.1447. Min Act: -0.1700
Data Index: 1298102 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9572. Min Range: -10.9572
Max Act: 10.1447. Min Act: -0.1700
Data Index: 5590512 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9572. Min Range: -10.9572
Max Act: 10.1447. Min Act: -0.1700
Data Index: 6469243 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9572. Min Range: -10.9572
Max Act: 10.0822. Min Act: -0.1700
Data Index: 5590510 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9572. Min Range: -10.9572
Max Act: 10.0822. Min Act: -0.1700
Data Index: 5590509 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9572. Min Range: -10.9572
Max Act: 10.0197. Min Act: -0.1700
Data Index: 6421719 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9572. Min Range: -10.9572
Max Act: 10.0197. Min Act: -0.1700
Data Index: 7061189 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9572. Min Range: -10.9572
Max Act: 10.0197. Min Act: -0.1700
Data Index: 6469242 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9572. Min Range: -10.9572
Max Act: 9.9572. Min Act: -0.1700
Data Index: 6360617 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9572. Min Range: -10.9572
Max Act: 9.9572. Min Act: -0.1700
Data Index: 3686392 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9572. Min Range: -10.9572
Max Act: 9.8322. Min Act: -0.1700
Data Index: 4452034 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9572. Min Range: -10.9572
Max Act: 9.8322. Min Act: -0.1700
Data Index: 678363 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9572. Min Range: -10.9572
Max Act: 9.8322. Min Act: -0.1700
Data Index: 4495014 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9572. Min Range: -10.9572
Max Act: 9.8322. Min Act: -0.1700
Data Index: 8036637 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19