Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2867 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.4462. Min Act: -0.1700
Data Index: 7507181 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.3837. Min Act: -0.1700
Data Index: 4266112 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.3524. Min Act: -0.1700
Data Index: 2699069 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.3212. Min Act: -0.1700
Data Index: 5475129 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.2274. Min Act: -0.1700
Data Index: 4905718 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.2274. Min Act: -0.1700
Data Index: 8720143 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.1962. Min Act: -0.1700
Data Index: 4962960 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.1649. Min Act: -0.1700
Data Index: 5260839 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.1649. Min Act: -0.1700
Data Index: 1687773 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.1649. Min Act: -0.1700
Data Index: 4266110 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.1649. Min Act: -0.1700
Data Index: 4573385 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.1024. Min Act: -0.1700
Data Index: 3953397 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.0399. Min Act: -0.1700
Data Index: 3719923 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.0712. Min Act: -0.1700
Data Index: 3703281 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.0399. Min Act: -0.1700
Data Index: 7125531 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.0399. Min Act: -0.1700
Data Index: 1936503 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.0087. Min Act: -0.1700
Data Index: 6949361 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4462. Min Range: -5.4462
Max Act: 4.9774. Min Act: -0.1700
Data Index: 69413 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.0087. Min Act: -0.1700
Data Index: 3126047 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.0399. Min Act: -0.1700
Data Index: 181698 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19