Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6389 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.9983. Min Act: -0.1700
Data Index: 3570785 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.9358. Min Act: -0.1700
Data Index: 6902412 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.9046. Min Act: -0.1700
Data Index: 7555788 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.8421. Min Act: -0.1700
Data Index: 7337027 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.8108. Min Act: -0.1700
Data Index: 6304930 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.8108. Min Act: -0.1700
Data Index: 4802891 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.8108. Min Act: -0.1700
Data Index: 3913359 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.7483. Min Act: -0.1700
Data Index: 2718081 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.7483. Min Act: -0.1700
Data Index: 6402942 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.7171. Min Act: -0.1700
Data Index: 3437481 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.7171. Min Act: -0.1700
Data Index: 7041766 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.6546. Min Act: -0.1700
Data Index: 78031 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.6546. Min Act: -0.1700
Data Index: 3055207 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.6233. Min Act: -0.1700
Data Index: 1774431 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.6233. Min Act: -0.1700
Data Index: 4815160 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.5921. Min Act: -0.1700
Data Index: 6440157 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.5921. Min Act: -0.1700
Data Index: 1516315 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.5921. Min Act: -0.1700
Data Index: 145412 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.5921. Min Act: -0.1700
Data Index: 232618 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9983. Min Range: -5.9983
Max Act: 5.5921. Min Act: -0.1700
Data Index: 4713695 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19