Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2655 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.6116. Min Act: -0.1700
Data Index: 1215367 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.4866. Min Act: -0.1700
Data Index: 6613310 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.4866. Min Act: -0.1700
Data Index: 963641 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.4866. Min Act: -0.1700
Data Index: 4303696 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.4553. Min Act: -0.1700
Data Index: 4691961 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.4553. Min Act: -0.1700
Data Index: 4211040 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.4553. Min Act: -0.1700
Data Index: 8399273 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.4241. Min Act: -0.1700
Data Index: 6211662 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.4241. Min Act: -0.1700
Data Index: 7826065 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.4553. Min Act: -0.1700
Data Index: 7043945 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.3928. Min Act: -0.1700
Data Index: 6850508 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.3928. Min Act: -0.1700
Data Index: 1198884 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.3616. Min Act: -0.1700
Data Index: 8145355 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.3303. Min Act: -0.1700
Data Index: 6635450 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.3303. Min Act: -0.1700
Data Index: 8181035 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.2991. Min Act: -0.1700
Data Index: 7778027 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.2991. Min Act: -0.1700
Data Index: 4979149 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.2991. Min Act: -0.1700
Data Index: 5622810 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.2678. Min Act: -0.1700
Data Index: 4355276 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6116. Min Range: -4.6116
Max Act: 4.2991. Min Act: -0.1700
Data Index: 2778742 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19