Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3594 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.8467. Min Act: -0.1700
Data Index: 4748852 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.7529. Min Act: -0.1700
Data Index: 4416249 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.6903. Min Act: -0.1700
Data Index: 3318463 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.6903. Min Act: -0.1700
Data Index: 3996284 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.6590. Min Act: -0.1700
Data Index: 1218210 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.6277. Min Act: -0.1700
Data Index: 4990448 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.6434. Min Act: -0.1700
Data Index: 4290530 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.6121. Min Act: -0.1700
Data Index: 6004098 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.5964. Min Act: -0.1700
Data Index: 2595313 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.5964. Min Act: -0.1700
Data Index: 7841550 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.5808. Min Act: -0.1700
Data Index: 4290531 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.5808. Min Act: -0.1700
Data Index: 5585756 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.5651. Min Act: -0.1700
Data Index: 3528172 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.5651. Min Act: -0.1700
Data Index: 2868943 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.5651. Min Act: -0.1700
Data Index: 8020824 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.5651. Min Act: -0.1700
Data Index: 5369708 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.5651. Min Act: -0.1700
Data Index: 7434543 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.5494. Min Act: -0.1700
Data Index: 1336442 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.5338. Min Act: -0.1700
Data Index: 6743443 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8467. Min Range: -3.8467
Max Act: 3.5181. Min Act: -0.1700
Data Index: 5480876 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19