Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2490 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.5341. Min Act: -0.1700
Data Index: 2479495 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.5341. Min Act: -0.1700
Data Index: 3844253 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.5028. Min Act: -0.1700
Data Index: 2923678 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.4403. Min Act: -0.1700
Data Index: 7175972 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.4403. Min Act: -0.1700
Data Index: 5743920 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.3778. Min Act: -0.1700
Data Index: 4398352 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.3778. Min Act: -0.1700
Data Index: 1416246 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.3153. Min Act: -0.1700
Data Index: 8210175 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.3153. Min Act: -0.1700
Data Index: 1874374 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.3153. Min Act: -0.1700
Data Index: 873178 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.3153. Min Act: -0.1700
Data Index: 5965125 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.2841. Min Act: -0.1700
Data Index: 7387178 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.2841. Min Act: -0.1700
Data Index: 6524340 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.2841. Min Act: -0.1700
Data Index: 2556400 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.2841. Min Act: -0.1700
Data Index: 4535085 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.2841. Min Act: -0.1700
Data Index: 1980424 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.2841. Min Act: -0.1700
Data Index: 6363612 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.2528. Min Act: -0.1700
Data Index: 3090959 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.2528. Min Act: -0.1700
Data Index: 2698093 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5341. Min Range: -5.5341
Max Act: 5.2528. Min Act: -0.1700
Data Index: 6952702 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19