Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1067 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1182. Min Range: -5.1182
Max Act: 5.1182. Min Act: -0.1700
Data Index: 4789832 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1182. Min Range: -5.1182
Max Act: 5.0557. Min Act: -0.1700
Data Index: 796900 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.9932. Min Act: -0.1700
Data Index: 7345960 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.9932. Min Act: -0.1700
Data Index: 1969148 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.9932. Min Act: -0.1700
Data Index: 7972352 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.9932. Min Act: -0.1700
Data Index: 276097 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.9620. Min Act: -0.1700
Data Index: 3188144 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.9620. Min Act: -0.1700
Data Index: 1304648 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.9307. Min Act: -0.1700
Data Index: 2519539 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.9620. Min Act: -0.1700
Data Index: 7883594 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.9307. Min Act: -0.1700
Data Index: 6148638 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.9620. Min Act: -0.1700
Data Index: 4653186 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.9307. Min Act: -0.1700
Data Index: 6039016 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.8995. Min Act: -0.1700
Data Index: 8513672 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.9307. Min Act: -0.1700
Data Index: 531144 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.9620. Min Act: -0.1700
Data Index: 2317921 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.8995. Min Act: -0.1700
Data Index: 2532111 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.8995. Min Act: -0.1700
Data Index: 7403579 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.8995. Min Act: -0.1700
Data Index: 6540294 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1182. Min Range: -5.1182
Max Act: 4.8995. Min Act: -0.1700
Data Index: 3851486 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19