Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.7233. Min Act: -0.1700
Data Index: 4462719 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.6608. Min Act: -0.1700
Data Index: 4462689 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.5983. Min Act: -0.1700
Data Index: 4462674 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.5983. Min Act: -0.1700
Data Index: 4462715 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.5670. Min Act: -0.1700
Data Index: 4462698 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.4733. Min Act: -0.1700
Data Index: 4462684 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.4108. Min Act: -0.1700
Data Index: 4462700 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.3170. Min Act: -0.1700
Data Index: 6792438 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.2858. Min Act: -0.1700
Data Index: 4462677 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.2858. Min Act: -0.1700
Data Index: 4462667 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.2545. Min Act: -0.1700
Data Index: 4462724 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.2233. Min Act: -0.1700
Data Index: 5378571 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.1920. Min Act: -0.1700
Data Index: 4462713 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.1295. Min Act: -0.1700
Data Index: 1042061 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.0983. Min Act: -0.1700
Data Index: 4967410 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.0983. Min Act: -0.1700
Data Index: 5509492 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.0983. Min Act: -0.1700
Data Index: 5509497 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.0358. Min Act: -0.1700
Data Index: 3117321 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.0045. Min Act: -0.1700
Data Index: 4462660 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7233. Min Range: -6.7233
Max Act: 6.0045. Min Act: -0.1700
Data Index: 4462679 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19