Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 127 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.5332. Min Act: -0.1700
Data Index: 2223801 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.5019. Min Act: -0.1700
Data Index: 2692998 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.4707. Min Act: -0.1700
Data Index: 2304710 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.4082. Min Act: -0.1700
Data Index: 4436762 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.2519. Min Act: -0.1700
Data Index: 2543551 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.2519. Min Act: -0.1700
Data Index: 7644574 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.2207. Min Act: -0.1700
Data Index: 7592043 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.2207. Min Act: -0.1700
Data Index: 8707362 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.1894. Min Act: -0.1700
Data Index: 8027442 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.1582. Min Act: -0.1700
Data Index: 4999606 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.1269. Min Act: -0.1700
Data Index: 5169617 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.1582. Min Act: -0.1700
Data Index: 3884110 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.1269. Min Act: -0.1700
Data Index: 3747585 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.1269. Min Act: -0.1700
Data Index: 1092446 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.1269. Min Act: -0.1700
Data Index: 7595550 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.1269. Min Act: -0.1700
Data Index: 6830927 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.0957. Min Act: -0.1700
Data Index: 3362057 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.0957. Min Act: -0.1700
Data Index: 2324357 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.0644. Min Act: -0.1700
Data Index: 1530969 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5332. Min Range: -6.5332
Max Act: 6.0644. Min Act: -0.1700
Data Index: 341902 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19