Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2911 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.7668. Min Act: -0.1700
Data Index: 1259156 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.6418. Min Act: -0.1700
Data Index: 7201054 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.5480. Min Act: -0.1700
Data Index: 8379193 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.4230. Min Act: -0.1700
Data Index: 2484358 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.4230. Min Act: -0.1700
Data Index: 421959 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.3605. Min Act: -0.1700
Data Index: 8067646 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.2980. Min Act: -0.1700
Data Index: 2348513 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.2668. Min Act: -0.1700
Data Index: 3400667 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.2355. Min Act: -0.1700
Data Index: 233818 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.2043. Min Act: -0.1700
Data Index: 7609043 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.2043. Min Act: -0.1700
Data Index: 7074949 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.2043. Min Act: -0.1700
Data Index: 7402649 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.2043. Min Act: -0.1700
Data Index: 2053976 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.1418. Min Act: -0.1700
Data Index: 4754964 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.1105. Min Act: -0.1700
Data Index: 686592 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.1105. Min Act: -0.1700
Data Index: 3084434 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.1418. Min Act: -0.1700
Data Index: 3002229 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.0793. Min Act: -0.1700
Data Index: 3368298 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.0793. Min Act: -0.1700
Data Index: 4752919 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7668. Min Range: -7.7668
Max Act: 7.0168. Min Act: -0.1700
Data Index: 498971 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19