Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2604 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.8338. Min Act: -0.1700
Data Index: 6305036 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.8338. Min Act: -0.1700
Data Index: 4964704 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.8020. Min Act: -0.1700
Data Index: 5792967 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.8179. Min Act: -0.1699
Data Index: 8293372 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.8020. Min Act: -0.1700
Data Index: 4284940 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.7861. Min Act: -0.1700
Data Index: 1450092 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.7382. Min Act: -0.1700
Data Index: 4742460 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.7382. Min Act: -0.1700
Data Index: 6749357 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.7222. Min Act: -0.1700
Data Index: 2075081 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.7382. Min Act: -0.1700
Data Index: 6475621 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.7382. Min Act: -0.1700
Data Index: 7814163 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.7222. Min Act: -0.1700
Data Index: 4980569 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.7062. Min Act: -0.1700
Data Index: 3324193 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.6902. Min Act: -0.1700
Data Index: 6702450 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.6742. Min Act: -0.1700
Data Index: 6475620 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.6902. Min Act: -0.1700
Data Index: 6152921 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.6902. Min Act: -0.1700
Data Index: 1132604 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.6742. Min Act: -0.1700
Data Index: 8450648 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.6742. Min Act: -0.1700
Data Index: 6454548 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8338. Min Range: -2.8338
Max Act: 2.6582. Min Act: -0.1700
Data Index: 1267390 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19