Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3936 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0611. Min Range: -6.0611
Max Act: 6.0611. Min Act: -0.1700
Data Index: 674692 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.9361. Min Act: -0.1700
Data Index: 2703154 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.9049. Min Act: -0.1700
Data Index: 671754 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.8424. Min Act: -0.1700
Data Index: 2341631 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.8111. Min Act: -0.1700
Data Index: 5040622 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.8111. Min Act: -0.1700
Data Index: 6018421 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.8111. Min Act: -0.1700
Data Index: 8661941 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.7799. Min Act: -0.1700
Data Index: 1915239 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.7799. Min Act: -0.1700
Data Index: 228585 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.7486. Min Act: -0.1700
Data Index: 317207 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.7799. Min Act: -0.1700
Data Index: 975324 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.7486. Min Act: -0.1700
Data Index: 2153677 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.7174. Min Act: -0.1700
Data Index: 2802644 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.7174. Min Act: -0.1700
Data Index: 193636 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.7174. Min Act: -0.1700
Data Index: 5418458 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.7486. Min Act: -0.1700
Data Index: 7659596 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.7174. Min Act: -0.1700
Data Index: 7498844 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.6549. Min Act: -0.1700
Data Index: 2171188 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.6861. Min Act: -0.1700
Data Index: 2239359 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0611. Min Range: -6.0611
Max Act: 5.6549. Min Act: -0.1700
Data Index: 6120068 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19