Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2326 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4838. Min Range: -6.4838
Max Act: 6.4838. Min Act: -0.1700
Data Index: 2569962 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4838. Min Range: -6.4838
Max Act: 6.3276. Min Act: -0.1700
Data Index: 1947679 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4838. Min Range: -6.4838
Max Act: 6.2338. Min Act: -0.1700
Data Index: 7762609 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4838. Min Range: -6.4838
Max Act: 6.1713. Min Act: -0.1700
Data Index: 7006153 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4838. Min Range: -6.4838
Max Act: 6.2026. Min Act: -0.1700
Data Index: 1947681 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4838. Min Range: -6.4838
Max Act: 6.1088. Min Act: -0.1700
Data Index: 1993106 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4838. Min Range: -6.4838
Max Act: 6.1401. Min Act: -0.1700
Data Index: 7306201 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4838. Min Range: -6.4838
Max Act: 6.0776. Min Act: -0.1700
Data Index: 1685216 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4838. Min Range: -6.4838
Max Act: 6.1088. Min Act: -0.1700
Data Index: 80914 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4838. Min Range: -6.4838
Max Act: 6.0463. Min Act: -0.1700
Data Index: 6512323 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4838. Min Range: -6.4838
Max Act: 6.0151. Min Act: -0.1700
Data Index: 4265926 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4838. Min Range: -6.4838
Max Act: 5.9838. Min Act: -0.1700
Data Index: 1128685 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4838. Min Range: -6.4838
Max Act: 5.9838. Min Act: -0.1700
Data Index: 5469613 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4838. Min Range: -6.4838
Max Act: 5.9526. Min Act: -0.1700
Data Index: 3739187 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4838. Min Range: -6.4838
Max Act: 5.9838. Min Act: -0.1700
Data Index: 132175 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4838. Min Range: -6.4838
Max Act: 5.9526. Min Act: -0.1700
Data Index: 2598831 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4838. Min Range: -6.4838
Max Act: 5.9213. Min Act: -0.1700
Data Index: 4583280 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4838. Min Range: -6.4838
Max Act: 5.8901. Min Act: -0.1700
Data Index: 2569968 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4838. Min Range: -6.4838
Max Act: 5.8901. Min Act: -0.1700
Data Index: 5775602 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4838. Min Range: -6.4838
Max Act: 5.8901. Min Act: -0.1700
Data Index: 4376363 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19