Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4654 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.7655. Min Act: -0.1700
Data Index: 479942 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.6717. Min Act: -0.1700
Data Index: 7355801 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.6405. Min Act: -0.1700
Data Index: 7106884 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.5780. Min Act: -0.1700
Data Index: 1695816 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.5780. Min Act: -0.1700
Data Index: 5409994 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.5467. Min Act: -0.1700
Data Index: 444094 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.5467. Min Act: -0.1700
Data Index: 5334968 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.5467. Min Act: -0.1700
Data Index: 4767425 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.5467. Min Act: -0.1700
Data Index: 1149713 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.5155. Min Act: -0.1700
Data Index: 5502461 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.5155. Min Act: -0.1700
Data Index: 3248288 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.5155. Min Act: -0.1700
Data Index: 181827 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.4842. Min Act: -0.1700
Data Index: 4201801 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.4842. Min Act: -0.1700
Data Index: 6408663 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.4842. Min Act: -0.1700
Data Index: 2963359 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.4842. Min Act: -0.1700
Data Index: 3878568 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.4530. Min Act: -0.1700
Data Index: 5753832 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.4217. Min Act: -0.1700
Data Index: 5897928 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.4530. Min Act: -0.1700
Data Index: 4619786 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7655. Min Range: -4.7655
Max Act: 4.4530. Min Act: -0.1700
Data Index: 6313813 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19