Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 648 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2169. Min Range: -6.2169
Max Act: 6.2169. Min Act: -0.1700
Data Index: 1879001 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2169. Min Range: -6.2169
Max Act: 6.1544. Min Act: -0.1700
Data Index: 7115297 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2169. Min Range: -6.2169
Max Act: 6.0606. Min Act: -0.1700
Data Index: 6247102 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2169. Min Range: -6.2169
Max Act: 6.0294. Min Act: -0.1700
Data Index: 8707668 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.9669. Min Act: -0.1700
Data Index: 1516770 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.9356. Min Act: -0.1700
Data Index: 4970875 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8731. Min Act: -0.1700
Data Index: 6951537 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8419. Min Act: -0.1700
Data Index: 7788172 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.9044. Min Act: -0.1700
Data Index: 2197494 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8731. Min Act: -0.1700
Data Index: 2485908 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8419. Min Act: -0.1700
Data Index: 5461895 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8419. Min Act: -0.1700
Data Index: 2207150 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8419. Min Act: -0.1700
Data Index: 7271040 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8106. Min Act: -0.1700
Data Index: 1896411 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8106. Min Act: -0.1700
Data Index: 2703079 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.8106. Min Act: -0.1700
Data Index: 5838396 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.7794. Min Act: -0.1700
Data Index: 965620 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.7794. Min Act: -0.1700
Data Index: 7339286 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.7794. Min Act: -0.1700
Data Index: 6161906 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2169. Min Range: -6.2169
Max Act: 5.7794. Min Act: -0.1700
Data Index: 6735716 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19