Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 184 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2970. Min Range: -7.2970
Max Act: 7.2970. Min Act: -0.1700
Data Index: 1915663 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2970. Min Range: -7.2970
Max Act: 7.2970. Min Act: -0.1700
Data Index: 5030321 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2970. Min Range: -7.2970
Max Act: 7.2658. Min Act: -0.1700
Data Index: 7569256 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2970. Min Range: -7.2970
Max Act: 7.2345. Min Act: -0.1700
Data Index: 812322 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2970. Min Range: -7.2970
Max Act: 7.1408. Min Act: -0.1700
Data Index: 2223206 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2970. Min Range: -7.2970
Max Act: 7.1095. Min Act: -0.1700
Data Index: 5080137 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2970. Min Range: -7.2970
Max Act: 7.1095. Min Act: -0.1700
Data Index: 5181795 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2970. Min Range: -7.2970
Max Act: 7.0158. Min Act: -0.1700
Data Index: 7096050 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2970. Min Range: -7.2970
Max Act: 7.0158. Min Act: -0.1700
Data Index: 7591711 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2970. Min Range: -7.2970
Max Act: 6.9845. Min Act: -0.1700
Data Index: 7030306 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2970. Min Range: -7.2970
Max Act: 6.9845. Min Act: -0.1700
Data Index: 7039064 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2970. Min Range: -7.2970
Max Act: 6.9845. Min Act: -0.1700
Data Index: 1320105 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2970. Min Range: -7.2970
Max Act: 6.9533. Min Act: -0.1700
Data Index: 5313881 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2970. Min Range: -7.2970
Max Act: 6.9533. Min Act: -0.1700
Data Index: 3173196 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2970. Min Range: -7.2970
Max Act: 6.9533. Min Act: -0.1700
Data Index: 781162 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2970. Min Range: -7.2970
Max Act: 6.9533. Min Act: -0.1700
Data Index: 4546562 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2970. Min Range: -7.2970
Max Act: 6.8908. Min Act: -0.1700
Data Index: 7745779 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2970. Min Range: -7.2970
Max Act: 6.9220. Min Act: -0.1700
Data Index: 7203262 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2970. Min Range: -7.2970
Max Act: 6.9220. Min Act: -0.1700
Data Index: 4387355 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2970. Min Range: -7.2970
Max Act: 6.9220. Min Act: -0.1700
Data Index: 429667 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19