Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8714. Min Range: -7.8714
Max Act: 7.8714. Min Act: -0.1700
Data Index: 2629852 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8714. Min Range: -7.8714
Max Act: 7.5277. Min Act: -0.1700
Data Index: 8829099 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8714. Min Range: -7.8714
Max Act: 7.4652. Min Act: -0.1700
Data Index: 8806515 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8714. Min Range: -7.8714
Max Act: 7.3714. Min Act: -0.1700
Data Index: 4937215 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8714. Min Range: -7.8714
Max Act: 7.2464. Min Act: -0.1700
Data Index: 2307941 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8714. Min Range: -7.8714
Max Act: 7.1839. Min Act: -0.1700
Data Index: 106802 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8714. Min Range: -7.8714
Max Act: 7.1527. Min Act: -0.1700
Data Index: 8306827 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8714. Min Range: -7.8714
Max Act: 7.0902. Min Act: -0.1700
Data Index: 5662378 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8714. Min Range: -7.8714
Max Act: 7.0902. Min Act: -0.1700
Data Index: 279643 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8714. Min Range: -7.8714
Max Act: 7.0589. Min Act: -0.1700
Data Index: 3872346 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8714. Min Range: -7.8714
Max Act: 7.0589. Min Act: -0.1700
Data Index: 6966422 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8714. Min Range: -7.8714
Max Act: 7.0277. Min Act: -0.1700
Data Index: 3780598 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8714. Min Range: -7.8714
Max Act: 7.0277. Min Act: -0.1700
Data Index: 2102020 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8714. Min Range: -7.8714
Max Act: 6.9652. Min Act: -0.1700
Data Index: 6660610 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8714. Min Range: -7.8714
Max Act: 6.8714. Min Act: -0.1700
Data Index: 2574659 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8714. Min Range: -7.8714
Max Act: 6.8402. Min Act: -0.1700
Data Index: 1576027 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8714. Min Range: -7.8714
Max Act: 6.8402. Min Act: -0.1700
Data Index: 8810660 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8714. Min Range: -7.8714
Max Act: 6.8714. Min Act: -0.1700
Data Index: 4623127 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8714. Min Range: -7.8714
Max Act: 6.8402. Min Act: -0.1700
Data Index: 3412111 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8714. Min Range: -7.8714
Max Act: 6.8089. Min Act: -0.1700
Data Index: 812316 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19