Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4608 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3366. Min Range: -6.3366
Max Act: 6.3366. Min Act: -0.1700
Data Index: 1941235 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3366. Min Range: -6.3366
Max Act: 6.0866. Min Act: -0.1700
Data Index: 7653638 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.9616. Min Act: -0.1700
Data Index: 6765146 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.9616. Min Act: -0.1700
Data Index: 6167520 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.9616. Min Act: -0.1700
Data Index: 6911812 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.9303. Min Act: -0.1700
Data Index: 1735017 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.9303. Min Act: -0.1700
Data Index: 1014186 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.8991. Min Act: -0.1700
Data Index: 4963470 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.8991. Min Act: -0.1700
Data Index: 5903570 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.8678. Min Act: -0.1700
Data Index: 1544356 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.8678. Min Act: -0.1700
Data Index: 8468154 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.8366. Min Act: -0.1700
Data Index: 3000381 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.8366. Min Act: -0.1700
Data Index: 4111369 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.8053. Min Act: -0.1700
Data Index: 820084 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.8366. Min Act: -0.1700
Data Index: 5183206 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.8053. Min Act: -0.1700
Data Index: 491102 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.8053. Min Act: -0.1700
Data Index: 3292514 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.7741. Min Act: -0.1700
Data Index: 4065077 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.7428. Min Act: -0.1700
Data Index: 3333577 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3366. Min Range: -6.3366
Max Act: 5.7428. Min Act: -0.1700
Data Index: 7329250 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19