Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3988 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.7053. Min Act: -0.1700
Data Index: 676683 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.6740. Min Act: -0.1700
Data Index: 3379095 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.6428. Min Act: -0.1700
Data Index: 149657 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.6115. Min Act: -0.1700
Data Index: 7133928 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.5803. Min Act: -0.1700
Data Index: 7397635 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.5490. Min Act: -0.1700
Data Index: 5339782 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.5490. Min Act: -0.1700
Data Index: 3986237 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.5178. Min Act: -0.1700
Data Index: 5764609 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.5490. Min Act: -0.1700
Data Index: 6322797 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.4553. Min Act: -0.1700
Data Index: 681951 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.4553. Min Act: -0.1700
Data Index: 4222644 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.4553. Min Act: -0.1700
Data Index: 1128031 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.4553. Min Act: -0.1700
Data Index: 4665673 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.4240. Min Act: -0.1700
Data Index: 6517593 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.4240. Min Act: -0.1700
Data Index: 8279268 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.4553. Min Act: -0.1700
Data Index: 4384183 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.4553. Min Act: -0.1700
Data Index: 3431749 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.4553. Min Act: -0.1700
Data Index: 1154486 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.4240. Min Act: -0.1700
Data Index: 2586049 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7053. Min Range: -4.7053
Max Act: 4.4240. Min Act: -0.1700
Data Index: 5127002 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19