Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4310 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.5263. Min Act: -0.1700
Data Index: 5711383 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.3388. Min Act: -0.1700
Data Index: 4234566 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.3701. Min Act: -0.1700
Data Index: 3032335 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2763. Min Act: -0.1700
Data Index: 4367958 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2451. Min Act: -0.1700
Data Index: 5176872 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2451. Min Act: -0.1700
Data Index: 5555170 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2138. Min Act: -0.1700
Data Index: 6009273 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2138. Min Act: -0.1700
Data Index: 1208120 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2451. Min Act: -0.1700
Data Index: 8573952 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2138. Min Act: -0.1700
Data Index: 874803 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.1826. Min Act: -0.1700
Data Index: 1137746 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.1826. Min Act: -0.1700
Data Index: 5097540 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.1826. Min Act: -0.1700
Data Index: 355410 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.1513. Min Act: -0.1700
Data Index: 3004162 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.1513. Min Act: -0.1700
Data Index: 8475194 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.1513. Min Act: -0.1700
Data Index: 1055569 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.1513. Min Act: -0.1700
Data Index: 7101445 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.1513. Min Act: -0.1700
Data Index: 70689 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.1513. Min Act: -0.1700
Data Index: 4951658 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.1201. Min Act: -0.1700
Data Index: 5801608 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19