Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 130 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0154. Min Range: -4.0154
Max Act: 4.0154. Min Act: -0.1700
Data Index: 5322004 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.9216. Min Act: -0.1700
Data Index: 3758364 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.9216. Min Act: -0.1700
Data Index: 8279992 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.9216. Min Act: -0.1700
Data Index: 7254519 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.8904. Min Act: -0.1700
Data Index: 1973429 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.8591. Min Act: -0.1700
Data Index: 5859712 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.8591. Min Act: -0.1700
Data Index: 1241785 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.8591. Min Act: -0.1700
Data Index: 8784723 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.8278. Min Act: -0.1700
Data Index: 2510000 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.8591. Min Act: -0.1700
Data Index: 890667 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.8278. Min Act: -0.1700
Data Index: 809930 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.7809. Min Act: -0.1700
Data Index: 1988929 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.7966. Min Act: -0.1700
Data Index: 121056 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.8278. Min Act: -0.1700
Data Index: 8714615 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.7809. Min Act: -0.1700
Data Index: 113602 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.7809. Min Act: -0.1700
Data Index: 6237454 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.7966. Min Act: -0.1700
Data Index: 2957946 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.7966. Min Act: -0.1700
Data Index: 8348227 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.7809. Min Act: -0.1700
Data Index: 4388972 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0154. Min Range: -4.0154
Max Act: 3.7653. Min Act: -0.1700
Data Index: 3337519 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19