Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1612 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.6537. Min Act: -0.1700
Data Index: 1264488 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.6537. Min Act: -0.1700
Data Index: 2609777 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.5286. Min Act: -0.1700
Data Index: 6601487 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.5286. Min Act: -0.1700
Data Index: 6514727 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.4974. Min Act: -0.1700
Data Index: 7959003 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.4349. Min Act: -0.1700
Data Index: 7494679 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.4036. Min Act: -0.1700
Data Index: 2632513 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.4349. Min Act: -0.1700
Data Index: 8524626 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.4349. Min Act: -0.1700
Data Index: 2637634 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.4036. Min Act: -0.1700
Data Index: 8050764 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.4036. Min Act: -0.1700
Data Index: 2923488 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.4349. Min Act: -0.1700
Data Index: 3200898 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.3411. Min Act: -0.1700
Data Index: 4163655 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.3411. Min Act: -0.1700
Data Index: 7404087 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.3724. Min Act: -0.1700
Data Index: 2734413 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.3724. Min Act: -0.1700
Data Index: 4218620 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.3411. Min Act: -0.1700
Data Index: 7399137 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.3411. Min Act: -0.1700
Data Index: 3038943 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.3411. Min Act: -0.1700
Data Index: 5502224 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6537. Min Range: -4.6537
Max Act: 4.3411. Min Act: -0.1700
Data Index: 4352795 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19