Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1201 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.9684. Min Act: -0.1700
Data Index: 6125505 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.7496. Min Act: -0.1700
Data Index: 6500945 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.6871. Min Act: -0.1700
Data Index: 5008982 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.6871. Min Act: -0.1700
Data Index: 3192155 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.6246. Min Act: -0.1700
Data Index: 144175 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.5621. Min Act: -0.1700
Data Index: 8448886 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.4996. Min Act: -0.1700
Data Index: 4453556 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.4996. Min Act: -0.1700
Data Index: 2298904 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.4684. Min Act: -0.1700
Data Index: 7215117 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.4996. Min Act: -0.1700
Data Index: 6044930 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.4684. Min Act: -0.1700
Data Index: 4608243 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.4371. Min Act: -0.1700
Data Index: 4458354 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.4371. Min Act: -0.1700
Data Index: 6129928 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.4059. Min Act: -0.1700
Data Index: 4896088 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.3746. Min Act: -0.1700
Data Index: 6080632 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.3746. Min Act: -0.1700
Data Index: 8013168 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.4059. Min Act: -0.1700
Data Index: 2497411 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.3434. Min Act: -0.1700
Data Index: 6076308 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.3434. Min Act: -0.1700
Data Index: 3429285 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9684. Min Range: -5.9684
Max Act: 5.3434. Min Act: -0.1700
Data Index: 1310762 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19