Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5052 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.5302. Min Act: -0.1700
Data Index: 8672376 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.4989. Min Act: -0.1700
Data Index: 3050523 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.4364. Min Act: -0.1700
Data Index: 4394033 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.4677. Min Act: -0.1700
Data Index: 1520305 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.4364. Min Act: -0.1700
Data Index: 7683158 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.4364. Min Act: -0.1700
Data Index: 5099695 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.4677. Min Act: -0.1700
Data Index: 4588041 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.4052. Min Act: -0.1700
Data Index: 3388207 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.4052. Min Act: -0.1700
Data Index: 2752786 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.4052. Min Act: -0.1700
Data Index: 3181596 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.3739. Min Act: -0.1700
Data Index: 436708 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.4052. Min Act: -0.1700
Data Index: 2858137 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.4052. Min Act: -0.1700
Data Index: 1949399 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.4052. Min Act: -0.1700
Data Index: 2931 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.3739. Min Act: -0.1700
Data Index: 6235339 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.3739. Min Act: -0.1700
Data Index: 6435773 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.3739. Min Act: -0.1700
Data Index: 4232176 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.3427. Min Act: -0.1700
Data Index: 375903 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.3427. Min Act: -0.1700
Data Index: 1359364 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.3427. Min Act: -0.1700
Data Index: 7536641 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19