Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3817 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.8307. Min Act: -0.1700
Data Index: 3491953 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.7370. Min Act: -0.1700
Data Index: 3491962 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.6745. Min Act: -0.1700
Data Index: 3491958 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.6432. Min Act: -0.1700
Data Index: 3491948 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.6432. Min Act: -0.1700
Data Index: 3491957 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.6120. Min Act: -0.1700
Data Index: 3491959 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.6120. Min Act: -0.1700
Data Index: 3491964 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.5495. Min Act: -0.1700
Data Index: 5651626 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.5182. Min Act: -0.1700
Data Index: 3853329 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.5495. Min Act: -0.1700
Data Index: 3491945 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.4870. Min Act: -0.1700
Data Index: 3491955 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.4870. Min Act: -0.1700
Data Index: 3491963 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.4245. Min Act: -0.1700
Data Index: 4130666 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.4245. Min Act: -0.1700
Data Index: 3491949 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.3932. Min Act: -0.1700
Data Index: 3491961 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.3932. Min Act: -0.1700
Data Index: 5651622 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.3932. Min Act: -0.1700
Data Index: 8509097 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.3932. Min Act: -0.1700
Data Index: 3491960 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.3620. Min Act: -0.1700
Data Index: 6587447 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8307. Min Range: -5.8307
Max Act: 5.3620. Min Act: -0.1700
Data Index: 265295 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19