Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2301 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.4040. Min Act: -0.1700
Data Index: 3240623 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.3728. Min Act: -0.1700
Data Index: 8675562 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.3103. Min Act: -0.1700
Data Index: 469876 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.3728. Min Act: -0.1700
Data Index: 6707014 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.2478. Min Act: -0.1700
Data Index: 7520975 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.1853. Min Act: -0.1700
Data Index: 5163996 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.2165. Min Act: -0.1700
Data Index: 8339271 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.1853. Min Act: -0.1700
Data Index: 4495272 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.1540. Min Act: -0.1700
Data Index: 1152297 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.1228. Min Act: -0.1700
Data Index: 3008995 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.0915. Min Act: -0.1700
Data Index: 2052421 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.0915. Min Act: -0.1700
Data Index: 8430774 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.0915. Min Act: -0.1700
Data Index: 8661107 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.0915. Min Act: -0.1700
Data Index: 8653690 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.0915. Min Act: -0.1700
Data Index: 1560023 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.0603. Min Act: -0.1700
Data Index: 2098858 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4040. Min Range: -6.4040
Max Act: 6.0290. Min Act: -0.1700
Data Index: 2103774 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4040. Min Range: -6.4040
Max Act: 5.9978. Min Act: -0.1700
Data Index: 4339321 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4040. Min Range: -6.4040
Max Act: 5.9978. Min Act: -0.1700
Data Index: 7537433 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4040. Min Range: -6.4040
Max Act: 5.9665. Min Act: -0.1700
Data Index: 6677087 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19