Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2434 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4230. Min Range: -7.4230
Max Act: 7.4230. Min Act: -0.1700
Data Index: 8116396 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4230. Min Range: -7.4230
Max Act: 7.1730. Min Act: -0.1700
Data Index: 5917771 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4230. Min Range: -7.4230
Max Act: 7.1418. Min Act: -0.1700
Data Index: 2523623 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4230. Min Range: -7.4230
Max Act: 7.1418. Min Act: -0.1700
Data Index: 6866752 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4230. Min Range: -7.4230
Max Act: 7.1418. Min Act: -0.1700
Data Index: 3200790 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4230. Min Range: -7.4230
Max Act: 7.0480. Min Act: -0.1700
Data Index: 8073965 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4230. Min Range: -7.4230
Max Act: 7.0168. Min Act: -0.1700
Data Index: 7489191 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4230. Min Range: -7.4230
Max Act: 7.0168. Min Act: -0.1700
Data Index: 49517 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4230. Min Range: -7.4230
Max Act: 6.9855. Min Act: -0.1700
Data Index: 5895029 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4230. Min Range: -7.4230
Max Act: 6.9855. Min Act: -0.1700
Data Index: 6058983 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4230. Min Range: -7.4230
Max Act: 6.9543. Min Act: -0.1700
Data Index: 3644462 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4230. Min Range: -7.4230
Max Act: 6.9543. Min Act: -0.1700
Data Index: 8772725 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4230. Min Range: -7.4230
Max Act: 6.9543. Min Act: -0.1700
Data Index: 6846104 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4230. Min Range: -7.4230
Max Act: 6.9230. Min Act: -0.1700
Data Index: 3059591 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4230. Min Range: -7.4230
Max Act: 6.9230. Min Act: -0.1700
Data Index: 2710701 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4230. Min Range: -7.4230
Max Act: 6.9230. Min Act: -0.1700
Data Index: 5364435 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4230. Min Range: -7.4230
Max Act: 6.9230. Min Act: -0.1700
Data Index: 1703599 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4230. Min Range: -7.4230
Max Act: 6.9230. Min Act: -0.1700
Data Index: 7921469 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4230. Min Range: -7.4230
Max Act: 6.8918. Min Act: -0.1700
Data Index: 1652745 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4230. Min Range: -7.4230
Max Act: 6.8918. Min Act: -0.1700
Data Index: 64980 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19