Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3748. Min Range: -6.3748
Max Act: 6.3748. Min Act: -0.1700
Data Index: 8676529 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.8748. Min Act: -0.1700
Data Index: 7787002 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.8123. Min Act: -0.1700
Data Index: 7298407 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.7810. Min Act: -0.1700
Data Index: 3799816 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.7810. Min Act: -0.1700
Data Index: 2062286 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.7810. Min Act: -0.1700
Data Index: 7277426 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.7185. Min Act: -0.1700
Data Index: 695546 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.7185. Min Act: -0.1700
Data Index: 1500909 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.7185. Min Act: -0.1700
Data Index: 6076468 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.5935. Min Act: -0.1700
Data Index: 2522945 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.5935. Min Act: -0.1700
Data Index: 5261818 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.5623. Min Act: -0.1700
Data Index: 3823925 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.5623. Min Act: -0.1700
Data Index: 2945660 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.5623. Min Act: -0.1700
Data Index: 8656044 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.5623. Min Act: -0.1700
Data Index: 221195 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.5310. Min Act: -0.1700
Data Index: 5320055 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.5310. Min Act: -0.1700
Data Index: 3219325 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.4998. Min Act: -0.1700
Data Index: 1046868 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.4685. Min Act: -0.1700
Data Index: 3617886 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3748. Min Range: -6.3748
Max Act: 5.4685. Min Act: -0.1700
Data Index: 1095973 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19