Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.8105. Min Act: -0.1700
Data Index: 6144454 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.7168. Min Act: -0.1700
Data Index: 2142086 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.6543. Min Act: -0.1700
Data Index: 7085457 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.6543. Min Act: -0.1700
Data Index: 3989127 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.6543. Min Act: -0.1700
Data Index: 6431520 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.6230. Min Act: -0.1700
Data Index: 4878688 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.5918. Min Act: -0.1700
Data Index: 7082092 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.5918. Min Act: -0.1700
Data Index: 4133908 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.5918. Min Act: -0.1700
Data Index: 4766101 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.5605. Min Act: -0.1700
Data Index: 8814310 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.5605. Min Act: -0.1700
Data Index: 4689778 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.5605. Min Act: -0.1700
Data Index: 8352200 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.5918. Min Act: -0.1700
Data Index: 5986287 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.5293. Min Act: -0.1700
Data Index: 3566841 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.5293. Min Act: -0.1700
Data Index: 4133912 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.4980. Min Act: -0.1700
Data Index: 2123712 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.4980. Min Act: -0.1700
Data Index: 1599575 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.4980. Min Act: -0.1700
Data Index: 8814309 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.4668. Min Act: -0.1700
Data Index: 4276518 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8105. Min Range: -5.8105
Max Act: 5.4668. Min Act: -0.1700
Data Index: 4133906 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19