Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3428 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.9104. Min Act: -0.1700
Data Index: 4167290 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.6916. Min Act: -0.1700
Data Index: 8189241 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.6916. Min Act: -0.1700
Data Index: 1731183 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.6916. Min Act: -0.1700
Data Index: 3281250 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.6604. Min Act: -0.1700
Data Index: 4103123 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.6604. Min Act: -0.1700
Data Index: 7713073 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.5979. Min Act: -0.1700
Data Index: 5315821 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.5979. Min Act: -0.1700
Data Index: 7432517 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.5354. Min Act: -0.1700
Data Index: 8714336 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.5979. Min Act: -0.1700
Data Index: 1460974 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.5354. Min Act: -0.1700
Data Index: 3481580 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.5041. Min Act: -0.1700
Data Index: 7670122 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.5041. Min Act: -0.1700
Data Index: 3544848 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.4729. Min Act: -0.1700
Data Index: 4736155 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.5041. Min Act: -0.1700
Data Index: 5950459 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.4104. Min Act: -0.1700
Data Index: 6730189 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.4104. Min Act: -0.1700
Data Index: 3788769 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.3791. Min Act: -0.1700
Data Index: 2298672 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.3791. Min Act: -0.1700
Data Index: 6065720 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9104. Min Range: -6.9104
Max Act: 6.3791. Min Act: -0.1700
Data Index: 117487 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19