Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0070. Min Range: -7.0070
Max Act: 7.0070. Min Act: -0.1700
Data Index: 5982556 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.9132. Min Act: -0.1700
Data Index: 7140933 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.8507. Min Act: -0.1700
Data Index: 1557571 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.6945. Min Act: -0.1700
Data Index: 7104029 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.6945. Min Act: -0.1700
Data Index: 5564174 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.6320. Min Act: -0.1700
Data Index: 3965781 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.5070. Min Act: -0.1700
Data Index: 6638556 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.4757. Min Act: -0.1700
Data Index: 4584519 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.4757. Min Act: -0.1700
Data Index: 5130876 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.5070. Min Act: -0.1700
Data Index: 729282 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.5070. Min Act: -0.1700
Data Index: 7480075 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.4445. Min Act: -0.1700
Data Index: 4066765 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.4445. Min Act: -0.1700
Data Index: 314849 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.3820. Min Act: -0.1700
Data Index: 8281751 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.3820. Min Act: -0.1700
Data Index: 1017784 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.3195. Min Act: -0.1700
Data Index: 5138394 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.3507. Min Act: -0.1700
Data Index: 1608784 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.3507. Min Act: -0.1700
Data Index: 3565229 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.3195. Min Act: -0.1700
Data Index: 7471829 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0070. Min Range: -7.0070
Max Act: 6.3195. Min Act: -0.1700
Data Index: 6419226 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19