Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1636 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0957. Min Range: -7.0957
Max Act: 7.0957. Min Act: -0.1700
Data Index: 183242 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.9395. Min Act: -0.1700
Data Index: 7894968 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.6895. Min Act: -0.1700
Data Index: 6346495 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.5957. Min Act: -0.1700
Data Index: 4554820 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.5645. Min Act: -0.1700
Data Index: 3142270 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.5332. Min Act: -0.1700
Data Index: 3192927 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.5020. Min Act: -0.1700
Data Index: 5099875 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.4707. Min Act: -0.1700
Data Index: 8371043 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.4082. Min Act: -0.1700
Data Index: 6214237 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.4082. Min Act: -0.1700
Data Index: 1357792 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.3770. Min Act: -0.1700
Data Index: 6959679 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.3770. Min Act: -0.1700
Data Index: 7396824 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.3770. Min Act: -0.1700
Data Index: 2667733 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.3457. Min Act: -0.1700
Data Index: 3976509 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.3457. Min Act: -0.1700
Data Index: 1036964 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.3145. Min Act: -0.1700
Data Index: 8739046 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.3145. Min Act: -0.1700
Data Index: 1156230 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.2832. Min Act: -0.1700
Data Index: 4285602 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.2520. Min Act: -0.1700
Data Index: 5800149 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0957. Min Range: -7.0957
Max Act: 6.3145. Min Act: -0.1700
Data Index: 821782 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19