Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.6654. Min Act: -0.1700
Data Index: 7916449 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.6654. Min Act: -0.1700
Data Index: 7716211 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.5716. Min Act: -0.1700
Data Index: 8141781 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.5404. Min Act: -0.1700
Data Index: 5154313 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.5404. Min Act: -0.1700
Data Index: 7657856 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.4779. Min Act: -0.1700
Data Index: 3319691 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.5091. Min Act: -0.1700
Data Index: 3613104 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.4154. Min Act: -0.1700
Data Index: 1988204 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.4154. Min Act: -0.1700
Data Index: 2152916 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.4154. Min Act: -0.1700
Data Index: 8283108 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.4154. Min Act: -0.1700
Data Index: 4754592 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.4154. Min Act: -0.1700
Data Index: 6577642 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.3529. Min Act: -0.1700
Data Index: 2985657 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.2904. Min Act: -0.1700
Data Index: 113744 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.2591. Min Act: -0.1700
Data Index: 296619 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.2904. Min Act: -0.1700
Data Index: 4004339 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.2279. Min Act: -0.1700
Data Index: 1295514 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.1654. Min Act: -0.1700
Data Index: 8673666 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.1966. Min Act: -0.1700
Data Index: 8805799 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6654. Min Range: -6.6654
Max Act: 6.1654. Min Act: -0.1700
Data Index: 1594427 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19