Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 46 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.4025. Min Act: -0.1700
Data Index: 5673259 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.4650. Min Act: -0.1700
Data Index: 5996939 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.3400. Min Act: -0.1700
Data Index: 1105794 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.3400. Min Act: -0.1700
Data Index: 2706812 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.3400. Min Act: -0.1700
Data Index: 295177 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.3088. Min Act: -0.1700
Data Index: 1533065 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.3088. Min Act: -0.1700
Data Index: 379650 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.3088. Min Act: -0.1700
Data Index: 4753720 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.3088. Min Act: -0.1700
Data Index: 7572629 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.3088. Min Act: -0.1700
Data Index: 3019759 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.2775. Min Act: -0.1700
Data Index: 6741144 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.2775. Min Act: -0.1700
Data Index: 4315525 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.2775. Min Act: -0.1700
Data Index: 3794711 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.2463. Min Act: -0.1700
Data Index: 6687047 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.1838. Min Act: -0.1700
Data Index: 1665403 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.2463. Min Act: -0.1700
Data Index: 3872006 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.2150. Min Act: -0.1700
Data Index: 5695006 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.1838. Min Act: -0.1700
Data Index: 4457515 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.1838. Min Act: -0.1700
Data Index: 1533086 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4650. Min Range: -5.4650
Max Act: 5.1838. Min Act: -0.1700
Data Index: 1555351 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19