Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6287 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4515. Min Range: -6.4515
Max Act: 6.4515. Min Act: -0.1700
Data Index: 2488480 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4515. Min Range: -6.4515
Max Act: 6.0140. Min Act: -0.1700
Data Index: 6496670 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.9515. Min Act: -0.1700
Data Index: 3616477 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.9828. Min Act: -0.1700
Data Index: 1335320 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.9828. Min Act: -0.1700
Data Index: 5427434 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.9515. Min Act: -0.1700
Data Index: 6836585 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.8890. Min Act: -0.1700
Data Index: 1157430 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.8890. Min Act: -0.1700
Data Index: 2725411 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.8890. Min Act: -0.1700
Data Index: 7005276 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.8890. Min Act: -0.1700
Data Index: 2321732 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.8578. Min Act: -0.1700
Data Index: 4964762 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.8578. Min Act: -0.1700
Data Index: 3955225 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.8265. Min Act: -0.1700
Data Index: 422828 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.8265. Min Act: -0.1700
Data Index: 5856234 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.7953. Min Act: -0.1700
Data Index: 7759598 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.7953. Min Act: -0.1700
Data Index: 3400687 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.7953. Min Act: -0.1700
Data Index: 6287100 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.7953. Min Act: -0.1700
Data Index: 8824203 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.7640. Min Act: -0.1700
Data Index: 383481 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4515. Min Range: -6.4515
Max Act: 5.7953. Min Act: -0.1700
Data Index: 7093915 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19