Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5790 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8140. Min Range: -7.8140
Max Act: 7.8140. Min Act: -0.1700
Data Index: 4722249 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.9390. Min Act: -0.1700
Data Index: 5177868 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.9078. Min Act: -0.1700
Data Index: 4979064 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.4703. Min Act: -0.1700
Data Index: 6650425 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.4390. Min Act: -0.1700
Data Index: 4828877 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.4078. Min Act: -0.1700
Data Index: 7038980 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.3140. Min Act: -0.1700
Data Index: 8289104 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.2515. Min Act: -0.1700
Data Index: 3609982 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.2203. Min Act: -0.1700
Data Index: 7735518 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.1890. Min Act: -0.1700
Data Index: 2218376 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.0640. Min Act: -0.1700
Data Index: 4564586 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.0640. Min Act: -0.1700
Data Index: 2734252 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.0640. Min Act: -0.1700
Data Index: 8149972 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.0328. Min Act: -0.1700
Data Index: 26625 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.0328. Min Act: -0.1700
Data Index: 8262616 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.0328. Min Act: -0.1700
Data Index: 6889808 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.0328. Min Act: -0.1700
Data Index: 3507498 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8140. Min Range: -7.8140
Max Act: 6.0640. Min Act: -0.1700
Data Index: 4426602 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8140. Min Range: -7.8140
Max Act: 5.9703. Min Act: -0.1700
Data Index: 3483998 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8140. Min Range: -7.8140
Max Act: 5.9703. Min Act: -0.1700
Data Index: 5923025 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19