Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2206 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.4154. Min Act: -0.1700
Data Index: 5356789 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.3056. Min Act: -0.1700
Data Index: 958845 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.2585. Min Act: -0.1700
Data Index: 492828 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.1956. Min Act: -0.1700
Data Index: 2667846 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.1799. Min Act: -0.1700
Data Index: 7846769 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.1484. Min Act: -0.1700
Data Index: 8093910 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.1327. Min Act: -0.1700
Data Index: 7565600 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.1642. Min Act: -0.1700
Data Index: 3364487 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.1327. Min Act: -0.1700
Data Index: 1440229 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.1169. Min Act: -0.1700
Data Index: 3130075 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.1012. Min Act: -0.1700
Data Index: 8559413 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.0854. Min Act: -0.1700
Data Index: 8234598 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.0854. Min Act: -0.1700
Data Index: 6314975 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.0854. Min Act: -0.1700
Data Index: 2550126 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.0854. Min Act: -0.1700
Data Index: 2514037 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.0696. Min Act: -0.1700
Data Index: 3789619 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.0539. Min Act: -0.1700
Data Index: 6113219 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.0854. Min Act: -0.1700
Data Index: 8397473 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.0854. Min Act: -0.1700
Data Index: 8279530 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4154. Min Range: -3.4154
Max Act: 3.0539. Min Act: -0.1700
Data Index: 4749949 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19