Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2023 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.3459. Min Act: -0.1700
Data Index: 5414316 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.2966. Min Act: -0.1700
Data Index: 349555 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.3131. Min Act: -0.1700
Data Index: 4514782 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.2637. Min Act: -0.1700
Data Index: 3311560 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.2802. Min Act: -0.1700
Data Index: 5953801 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.2637. Min Act: -0.1700
Data Index: 5763124 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.2472. Min Act: -0.1700
Data Index: 6259881 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.2472. Min Act: -0.1700
Data Index: 4369030 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.2472. Min Act: -0.1700
Data Index: 6817732 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.2306. Min Act: -0.1700
Data Index: 2370968 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.2306. Min Act: -0.1700
Data Index: 5033328 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.2306. Min Act: -0.1700
Data Index: 4059766 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.1975. Min Act: -0.1700
Data Index: 917209 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.1975. Min Act: -0.1700
Data Index: 2338924 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.1809. Min Act: -0.1700
Data Index: 352171 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.1975. Min Act: -0.1700
Data Index: 4786708 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.1809. Min Act: -0.1700
Data Index: 1021473 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.1809. Min Act: -0.1700
Data Index: 1021472 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.1809. Min Act: -0.1700
Data Index: 4846449 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3459. Min Range: -2.3459
Max Act: 2.1809. Min Act: -0.1700
Data Index: 5634412 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19