Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0510. Min Range: -10.0510
Max Act: 10.0510. Min Act: -0.1700
Data Index: 961330 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.9885. Min Act: -0.1700
Data Index: 8410486 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.8635. Min Act: -0.1700
Data Index: 2918835 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.8635. Min Act: -0.1700
Data Index: 8794382 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.7385. Min Act: -0.1700
Data Index: 8740871 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.8010. Min Act: -0.1700
Data Index: 2763159 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.7385. Min Act: -0.1700
Data Index: 3235377 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.7385. Min Act: -0.1700
Data Index: 582046 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.6760. Min Act: -0.1700
Data Index: 5987492 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.6760. Min Act: -0.1700
Data Index: 8330243 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.6135. Min Act: -0.1700
Data Index: 5009424 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.5510. Min Act: -0.1700
Data Index: 2761942 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.6135. Min Act: -0.1700
Data Index: 6948675 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.4885. Min Act: -0.1700
Data Index: 7926688 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.4885. Min Act: -0.1700
Data Index: 2999464 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.4885. Min Act: -0.1700
Data Index: 5673247 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.4885. Min Act: -0.1700
Data Index: 7721298 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.4260. Min Act: -0.1700
Data Index: 1925260 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.4260. Min Act: -0.1700
Data Index: 4021569 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0510. Min Range: -10.0510
Max Act: 9.4260. Min Act: -0.1700
Data Index: 4454859 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19