Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1670 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.4818. Min Act: -0.1700
Data Index: 6980863 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.3881. Min Act: -0.1700
Data Index: 93293 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2943. Min Act: -0.1700
Data Index: 6017155 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2943. Min Act: -0.1700
Data Index: 7907336 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2318. Min Act: -0.1700
Data Index: 8309975 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2631. Min Act: -0.1700
Data Index: 5702092 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2318. Min Act: -0.1700
Data Index: 4233178 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2006. Min Act: -0.1700
Data Index: 4233179 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1693. Min Act: -0.1700
Data Index: 7417511 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1693. Min Act: -0.1700
Data Index: 1130802 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1381. Min Act: -0.1700
Data Index: 6980864 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1068. Min Act: -0.1700
Data Index: 6725218 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.0756. Min Act: -0.1700
Data Index: 2097787 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.0756. Min Act: -0.1700
Data Index: 1784312 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1068. Min Act: -0.1700
Data Index: 4726652 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.0443. Min Act: -0.1700
Data Index: 3741170 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.0443. Min Act: -0.1700
Data Index: 6153074 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.0443. Min Act: -0.1700
Data Index: 4928434 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.0443. Min Act: -0.1700
Data Index: 7928878 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.0131. Min Act: -0.1700
Data Index: 507044 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19