Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 72 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.3668. Min Act: -0.1700
Data Index: 2187586 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.3043. Min Act: -0.1700
Data Index: 5912650 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.2731. Min Act: -0.1700
Data Index: 1920291 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.2106. Min Act: -0.1700
Data Index: 4017360 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.2106. Min Act: -0.1700
Data Index: 1066939 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.1168. Min Act: -0.1700
Data Index: 5851953 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.1168. Min Act: -0.1700
Data Index: 6820716 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.0856. Min Act: -0.1700
Data Index: 760625 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.0856. Min Act: -0.1700
Data Index: 8322199 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.0856. Min Act: -0.1700
Data Index: 1414553 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.0543. Min Act: -0.1700
Data Index: 4279969 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.0543. Min Act: -0.1700
Data Index: 7085755 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.0543. Min Act: -0.1700
Data Index: 5276845 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.0543. Min Act: -0.1700
Data Index: 5330181 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.0231. Min Act: -0.1700
Data Index: 2175049 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3668. Min Range: -6.3668
Max Act: 5.9918. Min Act: -0.1700
Data Index: 6904823 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3668. Min Range: -6.3668
Max Act: 5.9918. Min Act: -0.1700
Data Index: 2219163 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3668. Min Range: -6.3668
Max Act: 6.0231. Min Act: -0.1700
Data Index: 5544574 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3668. Min Range: -6.3668
Max Act: 5.9918. Min Act: -0.1700
Data Index: 3763393 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3668. Min Range: -6.3668
Max Act: 5.9918. Min Act: -0.1700
Data Index: 3433132 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19