Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5623 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.1450. Min Act: -0.1700
Data Index: 630635 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.1450. Min Act: -0.1700
Data Index: 2200262 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.1450. Min Act: -0.1700
Data Index: 6527680 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.1137. Min Act: -0.1700
Data Index: 4776020 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.0825. Min Act: -0.1700
Data Index: 38513 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.1137. Min Act: -0.1700
Data Index: 2752602 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.1137. Min Act: -0.1700
Data Index: 4071608 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.1137. Min Act: -0.1700
Data Index: 4477609 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.1137. Min Act: -0.1700
Data Index: 5487849 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.0825. Min Act: -0.1700
Data Index: 8015643 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.0825. Min Act: -0.1700
Data Index: 43599 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.0512. Min Act: -0.1700
Data Index: 7132263 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.0512. Min Act: -0.1700
Data Index: 4646285 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.0512. Min Act: -0.1700
Data Index: 2767556 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.0200. Min Act: -0.1700
Data Index: 7247348 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.0200. Min Act: -0.1700
Data Index: 6524396 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.0200. Min Act: -0.1700
Data Index: 2437522 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.0200. Min Act: -0.1700
Data Index: 3675776 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.0200. Min Act: -0.1700
Data Index: 4634117 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1450. Min Range: -4.1450
Max Act: 4.0200. Min Act: -0.1700
Data Index: 3353000 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19