Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.8986. Min Act: -0.1700
Data Index: 831877 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.8673. Min Act: -0.1700
Data Index: 1095901 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.7111. Min Act: -0.1700
Data Index: 4197390 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.6486. Min Act: -0.1700
Data Index: 2804145 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.6173. Min Act: -0.1700
Data Index: 4408770 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.6173. Min Act: -0.1700
Data Index: 3778293 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.6173. Min Act: -0.1700
Data Index: 7375027 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.6486. Min Act: -0.1700
Data Index: 1098097 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.5861. Min Act: -0.1700
Data Index: 7603476 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.5236. Min Act: -0.1700
Data Index: 4825781 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.4923. Min Act: -0.1700
Data Index: 7405092 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.4923. Min Act: -0.1700
Data Index: 4919732 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.4923. Min Act: -0.1700
Data Index: 5149478 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.4923. Min Act: -0.1700
Data Index: 1144375 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.4611. Min Act: -0.1700
Data Index: 7284974 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.4298. Min Act: -0.1700
Data Index: 6857164 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.4298. Min Act: -0.1700
Data Index: 7813881 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.3986. Min Act: -0.1700
Data Index: 7312756 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.3986. Min Act: -0.1700
Data Index: 2917766 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8986. Min Range: -6.8986
Max Act: 6.3673. Min Act: -0.1700
Data Index: 680588 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19