Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3768 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.3338. Min Act: -0.1700
Data Index: 4547812 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.3652. Min Act: -0.1700
Data Index: 5759647 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.3338. Min Act: -0.1700
Data Index: 6899216 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.3181. Min Act: -0.1700
Data Index: 6589997 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.3024. Min Act: -0.1700
Data Index: 5495079 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.2553. Min Act: -0.1700
Data Index: 6478087 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.2239. Min Act: -0.1700
Data Index: 3884078 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.2082. Min Act: -0.1700
Data Index: 2102900 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.2396. Min Act: -0.1700
Data Index: 7893182 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.2082. Min Act: -0.1700
Data Index: 532635 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.2082. Min Act: -0.1700
Data Index: 4953796 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.1925. Min Act: -0.1700
Data Index: 5258061 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.1925. Min Act: -0.1700
Data Index: 6345572 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.2082. Min Act: -0.1700
Data Index: 660121 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.1925. Min Act: -0.1700
Data Index: 5775136 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.1925. Min Act: -0.1700
Data Index: 7200025 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.1925. Min Act: -0.1700
Data Index: 3647892 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.1767. Min Act: -0.1700
Data Index: 4452030 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.1610. Min Act: -0.1700
Data Index: 5294818 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3652. Min Range: -3.3652
Max Act: 3.1610. Min Act: -0.1700
Data Index: 5854643 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19