Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 558 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.9386. Min Act: -0.1700
Data Index: 2206002 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.7199. Min Act: -0.1700
Data Index: 182909 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.3761. Min Act: -0.1700
Data Index: 7015323 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.3761. Min Act: -0.1700
Data Index: 2545712 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.3449. Min Act: -0.1700
Data Index: 7248026 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.2511. Min Act: -0.1700
Data Index: 8307073 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.2199. Min Act: -0.1700
Data Index: 1558443 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.2199. Min Act: -0.1700
Data Index: 7876190 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.2199. Min Act: -0.1700
Data Index: 4928215 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.1886. Min Act: -0.1700
Data Index: 1381767 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.1261. Min Act: -0.1700
Data Index: 2304179 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.0636. Min Act: -0.1700
Data Index: 4905399 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.0324. Min Act: -0.1700
Data Index: 3510392 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.0011. Min Act: -0.1700
Data Index: 7053716 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.0324. Min Act: -0.1700
Data Index: 5636259 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.0636. Min Act: -0.1700
Data Index: 7610896 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.0011. Min Act: -0.1700
Data Index: 2715766 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.0636. Min Act: -0.1700
Data Index: 324440 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9386. Min Range: -7.9386
Max Act: 6.9699. Min Act: -0.1700
Data Index: 6070761 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9386. Min Range: -7.9386
Max Act: 7.0011. Min Act: -0.1700
Data Index: 1114866 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19