Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 350 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.8298. Min Act: -0.1700
Data Index: 4641059 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.8610. Min Act: -0.1700
Data Index: 7553833 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.8298. Min Act: -0.1700
Data Index: 191278 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.8298. Min Act: -0.1700
Data Index: 8453841 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.8610. Min Act: -0.1700
Data Index: 7566002 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.7359. Min Act: -0.1700
Data Index: 8447503 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.7359. Min Act: -0.1700
Data Index: 3467622 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.7046. Min Act: -0.1700
Data Index: 1140029 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.6734. Min Act: -0.1700
Data Index: 6895958 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.7046. Min Act: -0.1700
Data Index: 4898225 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.7046. Min Act: -0.1700
Data Index: 3102635 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.6421. Min Act: -0.1700
Data Index: 4467362 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.6734. Min Act: -0.1700
Data Index: 4808623 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.6734. Min Act: -0.1700
Data Index: 8609154 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.6734. Min Act: -0.1700
Data Index: 2702250 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.6421. Min Act: -0.1700
Data Index: 3381470 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.6421. Min Act: -0.1700
Data Index: 3752542 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.6421. Min Act: -0.1700
Data Index: 28772 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.6421. Min Act: -0.1700
Data Index: 8203505 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8610. Min Range: -3.8610
Max Act: 3.6421. Min Act: -0.1700
Data Index: 6598112 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19