Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4814 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.4887. Min Act: -0.1678
Data Index: 3812593 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.3748. Min Act: -0.1698
Data Index: 7500572 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.3584. Min Act: -0.1647
Data Index: 3690271 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.3092. Min Act: -0.1700
Data Index: 6901964 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.2763. Min Act: -0.1700
Data Index: 4459375 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.2763. Min Act: -0.1548
Data Index: 5278668 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.2763. Min Act: -0.1700
Data Index: 7881308 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.2598. Min Act: -0.1690
Data Index: 8056694 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.2598. Min Act: -0.1700
Data Index: 3602696 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.2598. Min Act: -0.1700
Data Index: 3987002 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.2432. Min Act: -0.1700
Data Index: 900730 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.2598. Min Act: -0.1666
Data Index: 3129017 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.2432. Min Act: -0.1700
Data Index: 1090628 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.2432. Min Act: -0.1700
Data Index: 1536885 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.2432. Min Act: -0.1692
Data Index: 4314248 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.2267. Min Act: -0.1700
Data Index: 4539052 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.2101. Min Act: -0.1699
Data Index: 737195 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.1935. Min Act: -0.1700
Data Index: 2084195 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.1935. Min Act: -0.1700
Data Index: 3054327 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4887. Min Range: -2.4887
Max Act: 2.1935. Min Act: -0.1697
Data Index: 5278669 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19