Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3955 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.7503. Min Act: -0.1700
Data Index: 666175 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.7503. Min Act: -0.1700
Data Index: 1072925 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.7190. Min Act: -0.1700
Data Index: 5057956 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.7190. Min Act: -0.1700
Data Index: 5360791 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6878. Min Act: -0.1700
Data Index: 4939227 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6878. Min Act: -0.1700
Data Index: 7170452 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.7190. Min Act: -0.1700
Data Index: 4062689 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6878. Min Act: -0.1700
Data Index: 6912336 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6878. Min Act: -0.1700
Data Index: 3744072 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6878. Min Act: -0.1700
Data Index: 2974346 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6878. Min Act: -0.1700
Data Index: 6229701 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6565. Min Act: -0.1700
Data Index: 1821363 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6253. Min Act: -0.1700
Data Index: 4111218 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6565. Min Act: -0.1700
Data Index: 3465739 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6565. Min Act: -0.1700
Data Index: 3339441 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6565. Min Act: -0.1700
Data Index: 7820693 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6253. Min Act: -0.1700
Data Index: 3585365 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6253. Min Act: -0.1700
Data Index: 5579506 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6253. Min Act: -0.1700
Data Index: 3465741 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7503. Min Range: -4.7503
Max Act: 4.6253. Min Act: -0.1700
Data Index: 2205143 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19