Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3968 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1961. Min Range: -9.1961
Max Act: 9.1961. Min Act: -0.1700
Data Index: 8165916 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.9461. Min Act: -0.1700
Data Index: 7969656 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.8836. Min Act: -0.1700
Data Index: 4406656 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.9461. Min Act: -0.1700
Data Index: 8191249 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.8211. Min Act: -0.1700
Data Index: 3967429 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.8211. Min Act: -0.1700
Data Index: 6216493 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.7586. Min Act: -0.1700
Data Index: 4322096 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.7586. Min Act: -0.1700
Data Index: 6065125 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.7586. Min Act: -0.1700
Data Index: 5160930 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.6961. Min Act: -0.1700
Data Index: 561392 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.6336. Min Act: -0.1700
Data Index: 1154928 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.6336. Min Act: -0.1700
Data Index: 4925291 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.6336. Min Act: -0.1700
Data Index: 6908231 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.6336. Min Act: -0.1700
Data Index: 2787877 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.6336. Min Act: -0.1700
Data Index: 8705175 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.6336. Min Act: -0.1700
Data Index: 3210456 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.6336. Min Act: -0.1700
Data Index: 997456 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.5711. Min Act: -0.1700
Data Index: 1963652 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.5711. Min Act: -0.1700
Data Index: 1616739 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1961. Min Range: -9.1961
Max Act: 7.6336. Min Act: -0.1700
Data Index: 5619459 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19