Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 294 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1429. Min Range: -5.1429
Max Act: 5.1429. Min Act: -0.1700
Data Index: 5723072 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1429. Min Range: -5.1429
Max Act: 5.0804. Min Act: -0.1700
Data Index: 91014 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1429. Min Range: -5.1429
Max Act: 5.0179. Min Act: -0.1700
Data Index: 1736268 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.9866. Min Act: -0.1700
Data Index: 3632979 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.9554. Min Act: -0.1700
Data Index: 7780345 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.9241. Min Act: -0.1700
Data Index: 8675659 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.9241. Min Act: -0.1700
Data Index: 5997204 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.9241. Min Act: -0.1700
Data Index: 8422048 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.9241. Min Act: -0.1700
Data Index: 4432394 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.9241. Min Act: -0.1700
Data Index: 4857196 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.9241. Min Act: -0.1700
Data Index: 4524543 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.8929. Min Act: -0.1700
Data Index: 7695394 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.8929. Min Act: -0.1700
Data Index: 3502670 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.8616. Min Act: -0.1700
Data Index: 598247 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.8616. Min Act: -0.1700
Data Index: 8258702 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.8304. Min Act: -0.1700
Data Index: 5692390 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.8304. Min Act: -0.1700
Data Index: 4540351 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.8304. Min Act: -0.1700
Data Index: 7293152 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.7991. Min Act: -0.1700
Data Index: 4733538 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1429. Min Range: -5.1429
Max Act: 4.8304. Min Act: -0.1700
Data Index: 50348 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19