Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3665 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1643. Min Range: -3.1643
Max Act: 3.1643. Min Act: -0.1700
Data Index: 4525832 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.7527. Min Act: -0.1700
Data Index: 116381 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.7527. Min Act: -0.1700
Data Index: 7002331 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.7207. Min Act: -0.1700
Data Index: 954538 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.7367. Min Act: -0.1700
Data Index: 6182935 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.7367. Min Act: -0.1700
Data Index: 8447707 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.7367. Min Act: -0.1700
Data Index: 3090704 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.7207. Min Act: -0.1700
Data Index: 5144161 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.7207. Min Act: -0.1700
Data Index: 7311515 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.7367. Min Act: -0.1700
Data Index: 2251682 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.7047. Min Act: -0.1700
Data Index: 1914524 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.7047. Min Act: -0.1700
Data Index: 2867120 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.7047. Min Act: -0.1700
Data Index: 6088091 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.6887. Min Act: -0.1700
Data Index: 6949232 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.6887. Min Act: -0.1700
Data Index: 2572312 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.6887. Min Act: -0.1700
Data Index: 938273 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.6887. Min Act: -0.1700
Data Index: 5405307 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.6727. Min Act: -0.1700
Data Index: 6526901 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.6727. Min Act: -0.1700
Data Index: 1442421 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1643. Min Range: -3.1643
Max Act: 2.6727. Min Act: -0.1700
Data Index: 7557786 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19