Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1582 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0403. Min Range: -10.0403
Max Act: 10.0403. Min Act: -0.1700
Data Index: 5966383 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.7278. Min Act: -0.1700
Data Index: 898166 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.6028. Min Act: -0.1700
Data Index: 1143375 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.6028. Min Act: -0.1700
Data Index: 4555707 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.4153. Min Act: -0.1700
Data Index: 1322641 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.4153. Min Act: -0.1700
Data Index: 6073567 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.3528. Min Act: -0.1700
Data Index: 1458475 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.4153. Min Act: -0.1700
Data Index: 1593631 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.4153. Min Act: -0.1700
Data Index: 8375838 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.3528. Min Act: -0.1700
Data Index: 2939925 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.3528. Min Act: -0.1700
Data Index: 957004 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.3528. Min Act: -0.1700
Data Index: 4585764 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.4153. Min Act: -0.1700
Data Index: 8336341 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.3528. Min Act: -0.1700
Data Index: 3648171 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.2903. Min Act: -0.1700
Data Index: 8124352 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.2903. Min Act: -0.1700
Data Index: 2153040 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.2903. Min Act: -0.1700
Data Index: 7734644 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.2278. Min Act: -0.1700
Data Index: 2245250 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.2278. Min Act: -0.1700
Data Index: 3728173 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0403. Min Range: -10.0403
Max Act: 9.2278. Min Act: -0.1700
Data Index: 7654048 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19