Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5575 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4187. Min Range: -7.4187
Max Act: 7.4187. Min Act: -0.1700
Data Index: 1003163 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4187. Min Range: -7.4187
Max Act: 7.3562. Min Act: -0.1700
Data Index: 3577496 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4187. Min Range: -7.4187
Max Act: 7.3562. Min Act: -0.1700
Data Index: 6682782 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4187. Min Range: -7.4187
Max Act: 7.2312. Min Act: -0.1700
Data Index: 3475174 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4187. Min Range: -7.4187
Max Act: 7.2312. Min Act: -0.1700
Data Index: 7267413 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4187. Min Range: -7.4187
Max Act: 7.1374. Min Act: -0.1700
Data Index: 3975077 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4187. Min Range: -7.4187
Max Act: 7.1374. Min Act: -0.1700
Data Index: 3824283 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4187. Min Range: -7.4187
Max Act: 7.0749. Min Act: -0.1700
Data Index: 4267053 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4187. Min Range: -7.4187
Max Act: 7.0124. Min Act: -0.1700
Data Index: 5714053 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4187. Min Range: -7.4187
Max Act: 6.9812. Min Act: -0.1700
Data Index: 6053379 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4187. Min Range: -7.4187
Max Act: 6.9812. Min Act: -0.1700
Data Index: 6775733 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4187. Min Range: -7.4187
Max Act: 6.9499. Min Act: -0.1700
Data Index: 4104913 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4187. Min Range: -7.4187
Max Act: 6.9187. Min Act: -0.1700
Data Index: 6387239 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4187. Min Range: -7.4187
Max Act: 6.8562. Min Act: -0.1700
Data Index: 6878199 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4187. Min Range: -7.4187
Max Act: 6.8249. Min Act: -0.1700
Data Index: 3358954 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4187. Min Range: -7.4187
Max Act: 6.7937. Min Act: -0.1700
Data Index: 6257976 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4187. Min Range: -7.4187
Max Act: 6.7937. Min Act: -0.1700
Data Index: 1110943 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4187. Min Range: -7.4187
Max Act: 6.7312. Min Act: -0.1700
Data Index: 6451191 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4187. Min Range: -7.4187
Max Act: 6.7312. Min Act: -0.1700
Data Index: 7470726 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4187. Min Range: -7.4187
Max Act: 6.7624. Min Act: -0.1700
Data Index: 1686769 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19