Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.9534. Min Act: -0.1699
Data Index: 6705518 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.9023. Min Act: -0.1700
Data Index: 3894551 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.9194. Min Act: -0.1699
Data Index: 2511543 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8853. Min Act: -0.1700
Data Index: 2045214 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8853. Min Act: -0.1700
Data Index: 7701413 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8682. Min Act: -0.1700
Data Index: 5497127 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8682. Min Act: -0.1700
Data Index: 5683382 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8853. Min Act: -0.1700
Data Index: 3649895 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8853. Min Act: -0.1700
Data Index: 1379959 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8682. Min Act: -0.1700
Data Index: 5704924 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8682. Min Act: -0.1700
Data Index: 490979 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8682. Min Act: -0.1700
Data Index: 6457498 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8511. Min Act: -0.1700
Data Index: 1053124 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8853. Min Act: -0.1700
Data Index: 3844180 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8682. Min Act: -0.1700
Data Index: 1167389 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8511. Min Act: -0.1700
Data Index: 2061293 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8682. Min Act: -0.1700
Data Index: 4344223 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8682. Min Act: -0.1700
Data Index: 2907228 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8682. Min Act: -0.1700
Data Index: 1252260 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9534. Min Range: -1.9534
Max Act: 1.8682. Min Act: -0.1700
Data Index: 6438942 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19