Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1972 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.8213. Min Act: -0.1700
Data Index: 501347 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.7901. Min Act: -0.1700
Data Index: 6302619 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.7901. Min Act: -0.1700
Data Index: 3048709 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.6963. Min Act: -0.1700
Data Index: 1997627 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.6651. Min Act: -0.1700
Data Index: 632630 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.6338. Min Act: -0.1700
Data Index: 6845066 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.6651. Min Act: -0.1700
Data Index: 2230548 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.6026. Min Act: -0.1700
Data Index: 527868 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.6026. Min Act: -0.1700
Data Index: 6269615 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.6026. Min Act: -0.1700
Data Index: 2883632 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.5713. Min Act: -0.1700
Data Index: 6382206 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.5713. Min Act: -0.1700
Data Index: 8081768 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.6026. Min Act: -0.1700
Data Index: 4974637 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.5713. Min Act: -0.1700
Data Index: 7437511 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.5713. Min Act: -0.1700
Data Index: 4442143 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.5713. Min Act: -0.1700
Data Index: 720550 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.5713. Min Act: -0.1700
Data Index: 4407958 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.5401. Min Act: -0.1700
Data Index: 5137400 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.5401. Min Act: -0.1700
Data Index: 7385610 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8213. Min Range: -5.8213
Max Act: 5.5401. Min Act: -0.1700
Data Index: 8618058 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19