Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1458 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2570. Min Range: -6.2570
Max Act: 6.2570. Min Act: -0.1700
Data Index: 5976452 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2570. Min Range: -6.2570
Max Act: 6.1320. Min Act: -0.1700
Data Index: 8462777 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2570. Min Range: -6.2570
Max Act: 6.0070. Min Act: -0.1700
Data Index: 5511912 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2570. Min Range: -6.2570
Max Act: 6.0070. Min Act: -0.1700
Data Index: 7086780 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.9445. Min Act: -0.1700
Data Index: 2963160 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.9758. Min Act: -0.1700
Data Index: 4285608 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.9133. Min Act: -0.1700
Data Index: 4778192 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.8820. Min Act: -0.1700
Data Index: 8388366 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.8508. Min Act: -0.1700
Data Index: 3679617 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.8508. Min Act: -0.1700
Data Index: 5336269 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.8195. Min Act: -0.1700
Data Index: 1185440 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.8195. Min Act: -0.1700
Data Index: 3007831 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.7570. Min Act: -0.1700
Data Index: 3259068 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.7570. Min Act: -0.1700
Data Index: 1578675 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.7570. Min Act: -0.1700
Data Index: 8353872 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.7570. Min Act: -0.1700
Data Index: 2798360 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.7570. Min Act: -0.1700
Data Index: 5786610 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.7883. Min Act: -0.1700
Data Index: 1368879 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.7570. Min Act: -0.1700
Data Index: 8234423 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2570. Min Range: -6.2570
Max Act: 5.7570. Min Act: -0.1700
Data Index: 8153921 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19