Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 768 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1976. Min Range: -6.1976
Max Act: 6.1976. Min Act: -0.1700
Data Index: 607643 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.9163. Min Act: -0.1700
Data Index: 3613258 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.8851. Min Act: -0.1700
Data Index: 3216939 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.8538. Min Act: -0.1700
Data Index: 5649354 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.7913. Min Act: -0.1700
Data Index: 1571974 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.8226. Min Act: -0.1700
Data Index: 611021 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.7913. Min Act: -0.1700
Data Index: 611022 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.7601. Min Act: -0.1700
Data Index: 6565654 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.7601. Min Act: -0.1700
Data Index: 2138695 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.7601. Min Act: -0.1700
Data Index: 8315452 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.7288. Min Act: -0.1700
Data Index: 5756646 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.7288. Min Act: -0.1700
Data Index: 1818477 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.7288. Min Act: -0.1700
Data Index: 7897341 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.6976. Min Act: -0.1700
Data Index: 8383781 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.6976. Min Act: -0.1700
Data Index: 4364134 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.6976. Min Act: -0.1700
Data Index: 7931918 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.6976. Min Act: -0.1700
Data Index: 1571971 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.6663. Min Act: -0.1700
Data Index: 5667546 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.6663. Min Act: -0.1700
Data Index: 981882 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.6663. Min Act: -0.1700
Data Index: 1799040 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19