Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.8199. Min Act: -0.1700
Data Index: 1235174 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.5699. Min Act: -0.1700
Data Index: 6961153 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.5386. Min Act: -0.1700
Data Index: 948866 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.4761. Min Act: -0.1700
Data Index: 5836937 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.4449. Min Act: -0.1700
Data Index: 8601960 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.4449. Min Act: -0.1700
Data Index: 3370150 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.3824. Min Act: -0.1700
Data Index: 3130968 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.3824. Min Act: -0.1700
Data Index: 7410332 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.3511. Min Act: -0.1700
Data Index: 811413 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.3511. Min Act: -0.1700
Data Index: 5555670 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.3199. Min Act: -0.1700
Data Index: 8653439 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.2886. Min Act: -0.1700
Data Index: 5775293 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.2574. Min Act: -0.1700
Data Index: 187793 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.2886. Min Act: -0.1700
Data Index: 5195199 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.2574. Min Act: -0.1700
Data Index: 6824164 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.2574. Min Act: -0.1700
Data Index: 3368807 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.2261. Min Act: -0.1700
Data Index: 4822255 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.2574. Min Act: -0.1700
Data Index: 6045812 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.1949. Min Act: -0.1700
Data Index: 7262021 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8199. Min Range: -5.8199
Max Act: 5.2261. Min Act: -0.1700
Data Index: 6038058 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19