Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.8479. Min Act: -0.1700
Data Index: 735789 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.8479. Min Act: -0.1700
Data Index: 1619557 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.8479. Min Act: -0.1700
Data Index: 3313595 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.7854. Min Act: -0.1700
Data Index: 317582 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.8166. Min Act: -0.1700
Data Index: 1017301 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.7854. Min Act: -0.1700
Data Index: 1820571 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.7229. Min Act: -0.1700
Data Index: 6132314 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.6916. Min Act: -0.1700
Data Index: 2290026 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.6916. Min Act: -0.1700
Data Index: 2568645 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.6291. Min Act: -0.1700
Data Index: 3123883 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.6916. Min Act: -0.1700
Data Index: 6425894 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.6916. Min Act: -0.1700
Data Index: 6833305 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.6291. Min Act: -0.1700
Data Index: 7294991 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.6604. Min Act: -0.1700
Data Index: 3019241 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.5979. Min Act: -0.1700
Data Index: 7725213 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.6291. Min Act: -0.1700
Data Index: 8583628 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.5666. Min Act: -0.1700
Data Index: 2763138 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.6291. Min Act: -0.1700
Data Index: 8832113 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.5354. Min Act: -0.1700
Data Index: 3283301 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8479. Min Range: -4.8479
Max Act: 4.5666. Min Act: -0.1700
Data Index: 4165804 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19