Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3428 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0225. Min Range: -6.0225
Max Act: 6.0225. Min Act: -0.1700
Data Index: 6958294 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.9912. Min Act: -0.1700
Data Index: 4943344 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.9600. Min Act: -0.1700
Data Index: 7640218 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.9600. Min Act: -0.1700
Data Index: 993332 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.9287. Min Act: -0.1700
Data Index: 4802537 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.9287. Min Act: -0.1700
Data Index: 7552534 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.8975. Min Act: -0.1700
Data Index: 161653 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.8662. Min Act: -0.1700
Data Index: 3561634 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.8662. Min Act: -0.1700
Data Index: 7169463 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.8662. Min Act: -0.1700
Data Index: 4446616 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.8037. Min Act: -0.1700
Data Index: 6759515 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.7412. Min Act: -0.1700
Data Index: 4468296 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.7725. Min Act: -0.1700
Data Index: 3919569 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.7412. Min Act: -0.1700
Data Index: 1069846 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.7100. Min Act: -0.1700
Data Index: 8196625 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.7100. Min Act: -0.1700
Data Index: 7912984 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.7100. Min Act: -0.1700
Data Index: 5465002 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.7100. Min Act: -0.1700
Data Index: 8783296 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.7100. Min Act: -0.1700
Data Index: 3939529 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0225. Min Range: -6.0225
Max Act: 5.6475. Min Act: -0.1700
Data Index: 5747334 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19