Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4957 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.6893. Min Act: -0.1700
Data Index: 8650043 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.5331. Min Act: -0.1700
Data Index: 58687 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.5018. Min Act: -0.1700
Data Index: 5818202 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.5018. Min Act: -0.1700
Data Index: 883901 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.4393. Min Act: -0.1700
Data Index: 6277029 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.4081. Min Act: -0.1700
Data Index: 5097300 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.4081. Min Act: -0.1700
Data Index: 6277028 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.3768. Min Act: -0.1700
Data Index: 7791888 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.2831. Min Act: -0.1700
Data Index: 7160753 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.2831. Min Act: -0.1700
Data Index: 6762951 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.2518. Min Act: -0.1700
Data Index: 371752 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.2518. Min Act: -0.1700
Data Index: 23758 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.2518. Min Act: -0.1700
Data Index: 353835 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.2206. Min Act: -0.1700
Data Index: 8629569 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.1893. Min Act: -0.1700
Data Index: 5872488 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.1893. Min Act: -0.1700
Data Index: 8747885 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.2206. Min Act: -0.1700
Data Index: 4140196 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.1893. Min Act: -0.1700
Data Index: 3800833 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.1581. Min Act: -0.1700
Data Index: 3362377 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6893. Min Range: -5.6893
Max Act: 5.1581. Min Act: -0.1700
Data Index: 3732665 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19