Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7171. Min Range: -7.7171
Max Act: 7.7171. Min Act: -0.1700
Data Index: 5742736 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7171. Min Range: -7.7171
Max Act: 7.0296. Min Act: -0.1700
Data Index: 3274059 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.5921. Min Act: -0.1700
Data Index: 3295784 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.5296. Min Act: -0.1694
Data Index: 969849 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.4984. Min Act: -0.1700
Data Index: 2541856 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.4671. Min Act: -0.1700
Data Index: 7032118 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.4671. Min Act: -0.1700
Data Index: 3732301 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.4359. Min Act: -0.1700
Data Index: 3814120 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.4046. Min Act: -0.1700
Data Index: 8744427 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.3734. Min Act: -0.1700
Data Index: 4000294 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.3421. Min Act: -0.1700
Data Index: 7270402 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.3421. Min Act: -0.1700
Data Index: 4128376 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.2796. Min Act: -0.1698
Data Index: 7655526 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.2484. Min Act: -0.1700
Data Index: 2199719 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.2484. Min Act: -0.1700
Data Index: 1451418 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.2171. Min Act: -0.1700
Data Index: 2728233 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.2171. Min Act: -0.1700
Data Index: 5948474 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.2171. Min Act: -0.1700
Data Index: 3153402 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.1859. Min Act: -0.1700
Data Index: 2168290 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7171. Min Range: -7.7171
Max Act: 6.1859. Min Act: -0.1700
Data Index: 104240 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19