Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2670 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.4276. Min Act: -0.1700
Data Index: 8059963 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.4113. Min Act: -0.1700
Data Index: 6548165 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2966. Min Act: -0.1700
Data Index: 451033 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.3131. Min Act: -0.1700
Data Index: 6382610 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2966. Min Act: -0.1700
Data Index: 5783707 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2636. Min Act: -0.1700
Data Index: 3826782 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2471. Min Act: -0.1700
Data Index: 3305157 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2636. Min Act: -0.1700
Data Index: 7579073 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2471. Min Act: -0.1700
Data Index: 6466636 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2636. Min Act: -0.1700
Data Index: 6548170 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2471. Min Act: -0.1700
Data Index: 5305165 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2471. Min Act: -0.1700
Data Index: 4865851 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2306. Min Act: -0.1700
Data Index: 2418803 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2471. Min Act: -0.1700
Data Index: 1642471 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2306. Min Act: -0.1700
Data Index: 3977202 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2471. Min Act: -0.1700
Data Index: 4844471 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2306. Min Act: -0.1700
Data Index: 8119899 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2471. Min Act: -0.1700
Data Index: 3879168 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.2140. Min Act: -0.1700
Data Index: 425909 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4276. Min Range: -2.4276
Max Act: 2.1974. Min Act: -0.1700
Data Index: 7062896 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19