Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5268 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0674. Min Range: -8.0674
Max Act: 8.0674. Min Act: -0.1700
Data Index: 2234579 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0674. Min Range: -8.0674
Max Act: 7.5049. Min Act: -0.1700
Data Index: 1915939 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0674. Min Range: -8.0674
Max Act: 7.2862. Min Act: -0.1700
Data Index: 4713604 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0674. Min Range: -8.0674
Max Act: 7.2549. Min Act: -0.1700
Data Index: 896133 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0674. Min Range: -8.0674
Max Act: 7.1924. Min Act: -0.1700
Data Index: 4107486 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0674. Min Range: -8.0674
Max Act: 7.1924. Min Act: -0.1700
Data Index: 1271872 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0674. Min Range: -8.0674
Max Act: 7.2237. Min Act: -0.1700
Data Index: 6539480 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0674. Min Range: -8.0674
Max Act: 7.0362. Min Act: -0.1700
Data Index: 3515968 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0674. Min Range: -8.0674
Max Act: 7.0362. Min Act: -0.1700
Data Index: 5814442 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0674. Min Range: -8.0674
Max Act: 6.9737. Min Act: -0.1700
Data Index: 4083220 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0674. Min Range: -8.0674
Max Act: 6.9424. Min Act: -0.1700
Data Index: 147651 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0674. Min Range: -8.0674
Max Act: 6.9424. Min Act: -0.1700
Data Index: 4058076 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0674. Min Range: -8.0674
Max Act: 6.8174. Min Act: -0.1700
Data Index: 2959216 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0674. Min Range: -8.0674
Max Act: 6.7862. Min Act: -0.1700
Data Index: 2113271 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0674. Min Range: -8.0674
Max Act: 6.7862. Min Act: -0.1700
Data Index: 6498104 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0674. Min Range: -8.0674
Max Act: 6.7549. Min Act: -0.1700
Data Index: 8215842 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0674. Min Range: -8.0674
Max Act: 6.7237. Min Act: -0.1700
Data Index: 1195975 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0674. Min Range: -8.0674
Max Act: 6.7549. Min Act: -0.1700
Data Index: 4564029 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0674. Min Range: -8.0674
Max Act: 6.6924. Min Act: -0.1700
Data Index: 2111522 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0674. Min Range: -8.0674
Max Act: 6.6612. Min Act: -0.1700
Data Index: 322093 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19