Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.4171. Min Act: -0.1700
Data Index: 360192 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.3858. Min Act: -0.1700
Data Index: 7518835 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.3858. Min Act: -0.1700
Data Index: 1482194 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.3233. Min Act: -0.1700
Data Index: 7208067 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.2608. Min Act: -0.1700
Data Index: 3463120 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.2608. Min Act: -0.1700
Data Index: 1343124 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.2608. Min Act: -0.1700
Data Index: 3244341 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.2608. Min Act: -0.1700
Data Index: 1343123 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.2608. Min Act: -0.1700
Data Index: 4568938 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.2608. Min Act: -0.1700
Data Index: 8482618 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.1983. Min Act: -0.1700
Data Index: 7074283 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.2296. Min Act: -0.1700
Data Index: 971119 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.2296. Min Act: -0.1700
Data Index: 1077012 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.2296. Min Act: -0.1700
Data Index: 2963786 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.1983. Min Act: -0.1700
Data Index: 8653435 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.1671. Min Act: -0.1700
Data Index: 3617485 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.1671. Min Act: -0.1700
Data Index: 8344635 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.1671. Min Act: -0.1700
Data Index: 6409435 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.1671. Min Act: -0.1700
Data Index: 5730962 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4171. Min Range: -4.4171
Max Act: 4.1358. Min Act: -0.1700
Data Index: 4595790 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19