Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4140 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0656. Min Range: -5.0656
Max Act: 5.0656. Min Act: -0.1700
Data Index: 2103689 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.9406. Min Act: -0.1700
Data Index: 1269238 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.8781. Min Act: -0.1700
Data Index: 820061 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.8156. Min Act: -0.1700
Data Index: 6018448 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.7843. Min Act: -0.1700
Data Index: 1558859 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.7843. Min Act: -0.1700
Data Index: 234432 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.7843. Min Act: -0.1700
Data Index: 297144 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.7843. Min Act: -0.1700
Data Index: 4239433 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.7218. Min Act: -0.1700
Data Index: 2094457 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.6906. Min Act: -0.1700
Data Index: 1519684 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.6593. Min Act: -0.1700
Data Index: 2992437 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.6593. Min Act: -0.1700
Data Index: 5799448 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.6593. Min Act: -0.1700
Data Index: 5979834 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.6281. Min Act: -0.1700
Data Index: 2649901 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.6593. Min Act: -0.1700
Data Index: 7727953 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.5968. Min Act: -0.1700
Data Index: 3434347 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.5968. Min Act: -0.1700
Data Index: 4199462 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.5968. Min Act: -0.1700
Data Index: 1454236 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.5968. Min Act: -0.1700
Data Index: 5145192 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0656. Min Range: -5.0656
Max Act: 4.5968. Min Act: -0.1700
Data Index: 5894917 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19