Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 999 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.1937. Min Act: -0.1700
Data Index: 8815581 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.2250. Min Act: -0.1700
Data Index: 983109 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.1937. Min Act: -0.1700
Data Index: 6190678 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.2250. Min Act: -0.1700
Data Index: 4785153 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.1937. Min Act: -0.1700
Data Index: 832789 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.1937. Min Act: -0.1700
Data Index: 7620319 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.1312. Min Act: -0.1700
Data Index: 5019058 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.1937. Min Act: -0.1700
Data Index: 1622659 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.1312. Min Act: -0.1700
Data Index: 7658315 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.1625. Min Act: -0.1700
Data Index: 7038424 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.1312. Min Act: -0.1700
Data Index: 814734 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.0999. Min Act: -0.1700
Data Index: 2259530 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.0999. Min Act: -0.1700
Data Index: 2419434 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.0999. Min Act: -0.1700
Data Index: 2849885 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.0374. Min Act: -0.1700
Data Index: 1363659 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.0062. Min Act: -0.1700
Data Index: 5986069 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.0374. Min Act: -0.1700
Data Index: 2268127 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.0374. Min Act: -0.1700
Data Index: 1125421 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.0062. Min Act: -0.1700
Data Index: 4349951 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2250. Min Range: -4.2250
Max Act: 4.0062. Min Act: -0.1700
Data Index: 2730435 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19