Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4220 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.9707. Min Act: -0.1700
Data Index: 3247180 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.5644. Min Act: -0.1700
Data Index: 8129855 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.4082. Min Act: -0.1700
Data Index: 3065593 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.3457. Min Act: -0.1700
Data Index: 4283410 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.3144. Min Act: -0.1700
Data Index: 2849379 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.2832. Min Act: -0.1700
Data Index: 1974345 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.2519. Min Act: -0.1700
Data Index: 5539135 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.2519. Min Act: -0.1700
Data Index: 7920334 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.2519. Min Act: -0.1700
Data Index: 1559645 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.2832. Min Act: -0.1700
Data Index: 359603 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.2207. Min Act: -0.1700
Data Index: 1783177 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.1894. Min Act: -0.1700
Data Index: 1779127 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.1894. Min Act: -0.1700
Data Index: 1559153 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.1582. Min Act: -0.1700
Data Index: 3229514 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.1582. Min Act: -0.1700
Data Index: 6411037 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.1582. Min Act: -0.1700
Data Index: 1578074 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.1582. Min Act: -0.1700
Data Index: 4525922 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.1582. Min Act: -0.1700
Data Index: 6180640 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.1582. Min Act: -0.1700
Data Index: 1499078 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9707. Min Range: -5.9707
Max Act: 5.1582. Min Act: -0.1700
Data Index: 2849380 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19