Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3148 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.8642. Min Act: -0.1700
Data Index: 2354609 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.8329. Min Act: -0.1700
Data Index: 1671558 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.7392. Min Act: -0.1700
Data Index: 4197211 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.7392. Min Act: -0.1700
Data Index: 7041950 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.7704. Min Act: -0.1700
Data Index: 2138210 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.7392. Min Act: -0.1700
Data Index: 5098639 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.7392. Min Act: -0.1700
Data Index: 4717121 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.7392. Min Act: -0.1700
Data Index: 7550833 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.7079. Min Act: -0.1700
Data Index: 8456615 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.6767. Min Act: -0.1700
Data Index: 6242298 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.7079. Min Act: -0.1700
Data Index: 6865167 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.6767. Min Act: -0.1700
Data Index: 5998492 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.7079. Min Act: -0.1700
Data Index: 6079597 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.6767. Min Act: -0.1700
Data Index: 5864075 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.7079. Min Act: -0.1700
Data Index: 6865166 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.7079. Min Act: -0.1700
Data Index: 4970145 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.7079. Min Act: -0.1700
Data Index: 5408132 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.6767. Min Act: -0.1700
Data Index: 3559117 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.7079. Min Act: -0.1700
Data Index: 4990403 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8642. Min Range: -5.8642
Max Act: 5.6767. Min Act: -0.1700
Data Index: 5848233 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19