Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4438 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0668. Min Range: -6.0668
Max Act: 6.0668. Min Act: -0.1700
Data Index: 6110111 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.8168. Min Act: -0.1700
Data Index: 4183593 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.7855. Min Act: -0.1700
Data Index: 6113202 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.6918. Min Act: -0.1700
Data Index: 1375811 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.6605. Min Act: -0.1700
Data Index: 8349976 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.6605. Min Act: -0.1700
Data Index: 8776382 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.6293. Min Act: -0.1700
Data Index: 2025021 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.6293. Min Act: -0.1700
Data Index: 296581 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.6293. Min Act: -0.1700
Data Index: 244064 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.5980. Min Act: -0.1700
Data Index: 4399514 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.5668. Min Act: -0.1700
Data Index: 4561005 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.5668. Min Act: -0.1700
Data Index: 2750202 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.5980. Min Act: -0.1700
Data Index: 1569412 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.5355. Min Act: -0.1700
Data Index: 4805059 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.5668. Min Act: -0.1700
Data Index: 7902513 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.5043. Min Act: -0.1700
Data Index: 2788430 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.5043. Min Act: -0.1700
Data Index: 6764141 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.5043. Min Act: -0.1700
Data Index: 2524482 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.5355. Min Act: -0.1700
Data Index: 8270516 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0668. Min Range: -6.0668
Max Act: 5.4730. Min Act: -0.1700
Data Index: 7173035 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19