Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7900. Min Range: -7.7900
Max Act: 7.7900. Min Act: -0.1700
Data Index: 4181732 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7900. Min Range: -7.7900
Max Act: 7.6963. Min Act: -0.1700
Data Index: 7700073 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7900. Min Range: -7.7900
Max Act: 7.6025. Min Act: -0.1700
Data Index: 4172837 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7900. Min Range: -7.7900
Max Act: 7.3213. Min Act: -0.1700
Data Index: 1350902 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7900. Min Range: -7.7900
Max Act: 7.1025. Min Act: -0.1700
Data Index: 3478980 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7900. Min Range: -7.7900
Max Act: 7.0713. Min Act: -0.1700
Data Index: 2686197 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7900. Min Range: -7.7900
Max Act: 7.0713. Min Act: -0.1700
Data Index: 4073916 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7900. Min Range: -7.7900
Max Act: 7.0400. Min Act: -0.1700
Data Index: 4180377 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7900. Min Range: -7.7900
Max Act: 7.0400. Min Act: -0.1700
Data Index: 1119803 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7900. Min Range: -7.7900
Max Act: 7.0400. Min Act: -0.1700
Data Index: 4921027 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7900. Min Range: -7.7900
Max Act: 7.0088. Min Act: -0.1700
Data Index: 3001206 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7900. Min Range: -7.7900
Max Act: 6.9775. Min Act: -0.1700
Data Index: 628624 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7900. Min Range: -7.7900
Max Act: 6.9463. Min Act: -0.1700
Data Index: 4537112 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7900. Min Range: -7.7900
Max Act: 6.9775. Min Act: -0.1700
Data Index: 409599 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7900. Min Range: -7.7900
Max Act: 6.9463. Min Act: -0.1700
Data Index: 5164626 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7900. Min Range: -7.7900
Max Act: 6.9150. Min Act: -0.1700
Data Index: 946589 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7900. Min Range: -7.7900
Max Act: 6.8525. Min Act: -0.1700
Data Index: 1371337 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7900. Min Range: -7.7900
Max Act: 6.8525. Min Act: -0.1700
Data Index: 3477050 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7900. Min Range: -7.7900
Max Act: 6.8213. Min Act: -0.1700
Data Index: 2360692 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7900. Min Range: -7.7900
Max Act: 6.8213. Min Act: -0.1700
Data Index: 4591995 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19