Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6262 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.7617. Min Act: -0.1700
Data Index: 7642714 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.7148. Min Act: -0.1700
Data Index: 6459911 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.6522. Min Act: -0.1700
Data Index: 6371285 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.6522. Min Act: -0.1700
Data Index: 4805702 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.6366. Min Act: -0.1700
Data Index: 6300348 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.6210. Min Act: -0.1700
Data Index: 6220423 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.5427. Min Act: -0.1700
Data Index: 3144962 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.5427. Min Act: -0.1700
Data Index: 6927728 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.5270. Min Act: -0.1700
Data Index: 4521069 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.5114. Min Act: -0.1700
Data Index: 7084139 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.5270. Min Act: -0.1700
Data Index: 3600435 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.4957. Min Act: -0.1700
Data Index: 7007336 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.4800. Min Act: -0.1700
Data Index: 5851582 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.4800. Min Act: -0.1700
Data Index: 5692046 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.4800. Min Act: -0.1700
Data Index: 4867745 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.4800. Min Act: -0.1700
Data Index: 3342109 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.4487. Min Act: -0.1700
Data Index: 8243762 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.4487. Min Act: -0.1700
Data Index: 2086228 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.4644. Min Act: -0.1700
Data Index: 965909 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7617. Min Range: -3.7617
Max Act: 3.4644. Min Act: -0.1700
Data Index: 8225420 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19