Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 928 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.2561. Min Range: -14.2561
Max Act: 14.2561. Min Act: -0.1698
Data Index: 3747072 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.2561. Min Range: -14.2561
Max Act: 14.1936. Min Act: -0.1695
Data Index: 520512 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.2561. Min Range: -14.2561
Max Act: 14.1936. Min Act: -0.1699
Data Index: 7689536 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.2561. Min Range: -14.2561
Max Act: 14.0686. Min Act: -0.1695
Data Index: 5434803 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.9436. Min Act: -0.1698
Data Index: 485675 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.9436. Min Act: -0.1700
Data Index: 8466377 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.8811. Min Act: -0.1700
Data Index: 8161903 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.8811. Min Act: -0.1670
Data Index: 5120053 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.8811. Min Act: -0.1700
Data Index: 4403090 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.8186. Min Act: -0.1700
Data Index: 3629597 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.8186. Min Act: -0.1687
Data Index: 5633838 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.7561. Min Act: -0.1687
Data Index: 4106573 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.7561. Min Act: -0.1698
Data Index: 1201870 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.6936. Min Act: -0.1700
Data Index: 2553159 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.6936. Min Act: -0.1700
Data Index: 2125188 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.7561. Min Act: -0.1699
Data Index: 2473854 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.6936. Min Act: -0.1700
Data Index: 3983545 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.6936. Min Act: -0.1694
Data Index: 6146073 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.6936. Min Act: -0.1678
Data Index: 8453873 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.2561. Min Range: -14.2561
Max Act: 13.6936. Min Act: -0.1696
Data Index: 3231951 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19