Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3068 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0263. Min Range: -7.0263
Max Act: 7.0263. Min Act: -0.1700
Data Index: 2602407 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.6825. Min Act: -0.1700
Data Index: 7183202 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.4638. Min Act: -0.1700
Data Index: 219537 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.4325. Min Act: -0.1700
Data Index: 8420410 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.3388. Min Act: -0.1700
Data Index: 4689869 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.3075. Min Act: -0.1700
Data Index: 3435290 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.3388. Min Act: -0.1700
Data Index: 7313571 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.2763. Min Act: -0.1700
Data Index: 2865593 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.2450. Min Act: -0.1700
Data Index: 1781890 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.2450. Min Act: -0.1700
Data Index: 3905076 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.1825. Min Act: -0.1700
Data Index: 6279738 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.2138. Min Act: -0.1700
Data Index: 1574644 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.2138. Min Act: -0.1700
Data Index: 1374876 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.1513. Min Act: -0.1700
Data Index: 199120 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.1200. Min Act: -0.1700
Data Index: 5371553 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.1200. Min Act: -0.1700
Data Index: 5662201 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.1200. Min Act: -0.1700
Data Index: 4324192 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.1200. Min Act: -0.1700
Data Index: 1707299 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.0888. Min Act: -0.1700
Data Index: 6289883 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0263. Min Range: -7.0263
Max Act: 6.0888. Min Act: -0.1700
Data Index: 4101487 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19