Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2134 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.8043. Min Act: -0.1700
Data Index: 4051205 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.7418. Min Act: -0.1700
Data Index: 5321328 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.7105. Min Act: -0.1700
Data Index: 4803609 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.6480. Min Act: -0.1700
Data Index: 7458925 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.5855. Min Act: -0.1700
Data Index: 7885377 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.5543. Min Act: -0.1700
Data Index: 2260545 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.5543. Min Act: -0.1700
Data Index: 6813635 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.5543. Min Act: -0.1700
Data Index: 4538105 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.5230. Min Act: -0.1700
Data Index: 8693591 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.4605. Min Act: -0.1700
Data Index: 4682051 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.4605. Min Act: -0.1700
Data Index: 71187 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.4605. Min Act: -0.1700
Data Index: 6052662 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.4293. Min Act: -0.1700
Data Index: 7231641 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.4293. Min Act: -0.1700
Data Index: 2700330 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.3980. Min Act: -0.1700
Data Index: 6383425 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.4293. Min Act: -0.1700
Data Index: 7231642 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.4293. Min Act: -0.1700
Data Index: 71186 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.4293. Min Act: -0.1700
Data Index: 7458926 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.3980. Min Act: -0.1700
Data Index: 5211732 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8043. Min Range: -4.8043
Max Act: 4.3668. Min Act: -0.1700
Data Index: 4100107 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19