Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4089 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.8770. Min Act: -0.1700
Data Index: 7853604 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.8770. Min Act: -0.1700
Data Index: 3539435 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.8458. Min Act: -0.1700
Data Index: 4060315 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.7208. Min Act: -0.1700
Data Index: 3947595 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.6895. Min Act: -0.1700
Data Index: 8427224 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.6270. Min Act: -0.1700
Data Index: 5681118 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.6270. Min Act: -0.1700
Data Index: 6609651 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.6270. Min Act: -0.1700
Data Index: 301976 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.5958. Min Act: -0.1700
Data Index: 4130606 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.5645. Min Act: -0.1700
Data Index: 2348418 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.5958. Min Act: -0.1700
Data Index: 6706562 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.5958. Min Act: -0.1700
Data Index: 3252890 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.5958. Min Act: -0.1700
Data Index: 939145 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.5645. Min Act: -0.1700
Data Index: 6508772 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.5645. Min Act: -0.1700
Data Index: 7405170 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.5645. Min Act: -0.1700
Data Index: 2297045 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.5333. Min Act: -0.1700
Data Index: 5610110 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.5333. Min Act: -0.1700
Data Index: 4479231 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.5020. Min Act: -0.1700
Data Index: 301971 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8770. Min Range: -5.8770
Max Act: 5.5020. Min Act: -0.1700
Data Index: 3435152 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19