Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.4657. Min Act: -0.1700
Data Index: 4134550 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.4345. Min Act: -0.1700
Data Index: 1176349 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.4345. Min Act: -0.1700
Data Index: 2962755 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.3407. Min Act: -0.1700
Data Index: 2131021 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.3095. Min Act: -0.1700
Data Index: 1783422 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.3095. Min Act: -0.1700
Data Index: 4463918 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.2782. Min Act: -0.1700
Data Index: 1687492 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.2782. Min Act: -0.1700
Data Index: 4174519 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.2782. Min Act: -0.1700
Data Index: 8566369 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.2157. Min Act: -0.1700
Data Index: 7787200 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.1845. Min Act: -0.1700
Data Index: 3759599 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.1845. Min Act: -0.1700
Data Index: 3074492 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.1532. Min Act: -0.1700
Data Index: 3975792 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.0907. Min Act: -0.1700
Data Index: 7260759 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.1220. Min Act: -0.1700
Data Index: 8541942 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.0907. Min Act: -0.1700
Data Index: 1776639 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.0595. Min Act: -0.1700
Data Index: 7250208 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.0595. Min Act: -0.1700
Data Index: 1809504 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.0282. Min Act: -0.1700
Data Index: 5041651 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4657. Min Range: -6.4657
Max Act: 6.0282. Min Act: -0.1700
Data Index: 2767872 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19