Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0020. Min Range: -6.0020
Max Act: 6.0020. Min Act: -0.1700
Data Index: 1078724 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.9707. Min Act: -0.1700
Data Index: 4997093 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.9082. Min Act: -0.1700
Data Index: 8649117 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.9082. Min Act: -0.1700
Data Index: 1850240 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.8770. Min Act: -0.1700
Data Index: 7436068 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.8145. Min Act: -0.1700
Data Index: 2532160 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.7832. Min Act: -0.1700
Data Index: 5690917 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.7832. Min Act: -0.1700
Data Index: 6375421 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.7520. Min Act: -0.1700
Data Index: 7603513 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.6895. Min Act: -0.1700
Data Index: 7518617 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.7207. Min Act: -0.1700
Data Index: 2378651 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.6895. Min Act: -0.1700
Data Index: 836030 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.6895. Min Act: -0.1700
Data Index: 6236830 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.6582. Min Act: -0.1700
Data Index: 7603515 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.7207. Min Act: -0.1700
Data Index: 6208135 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.6895. Min Act: -0.1700
Data Index: 4002646 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.6895. Min Act: -0.1700
Data Index: 7155190 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.6582. Min Act: -0.1700
Data Index: 6139708 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.6582. Min Act: -0.1700
Data Index: 810678 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0020. Min Range: -6.0020
Max Act: 5.6270. Min Act: -0.1700
Data Index: 572126 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19