Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4077 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2160. Min Range: -8.2160
Max Act: 8.2160. Min Act: -0.1700
Data Index: 6682564 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2160. Min Range: -8.2160
Max Act: 8.0285. Min Act: -0.1700
Data Index: 5966338 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.9035. Min Act: -0.1700
Data Index: 6663274 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.8722. Min Act: -0.1700
Data Index: 8586536 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.8410. Min Act: -0.1700
Data Index: 4447113 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.7785. Min Act: -0.1700
Data Index: 4228808 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.7785. Min Act: -0.1700
Data Index: 584099 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.7472. Min Act: -0.1700
Data Index: 584100 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.6847. Min Act: -0.1700
Data Index: 4099172 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.6535. Min Act: -0.1700
Data Index: 5126226 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.6535. Min Act: -0.1700
Data Index: 5928969 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.5910. Min Act: -0.1700
Data Index: 2788525 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.5910. Min Act: -0.1700
Data Index: 4099171 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.5910. Min Act: -0.1700
Data Index: 7521881 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.5597. Min Act: -0.1700
Data Index: 2967462 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.5597. Min Act: -0.1700
Data Index: 913151 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.5597. Min Act: -0.1700
Data Index: 3859772 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.5597. Min Act: -0.1700
Data Index: 4945614 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.5597. Min Act: -0.1700
Data Index: 2342368 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2160. Min Range: -8.2160
Max Act: 7.4972. Min Act: -0.1700
Data Index: 6127642 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19