Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 225 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.3778. Min Act: -0.1700
Data Index: 8713692 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.3778. Min Act: -0.1700
Data Index: 2448540 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.3465. Min Act: -0.1700
Data Index: 1943851 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.3465. Min Act: -0.1700
Data Index: 8107215 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.3153. Min Act: -0.1700
Data Index: 4614558 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.3153. Min Act: -0.1700
Data Index: 7125180 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.3153. Min Act: -0.1700
Data Index: 5345186 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.3465. Min Act: -0.1700
Data Index: 2066791 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.3153. Min Act: -0.1700
Data Index: 8805176 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.3153. Min Act: -0.1700
Data Index: 6789638 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.3153. Min Act: -0.1700
Data Index: 6189394 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.2840. Min Act: -0.1700
Data Index: 4191811 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.2840. Min Act: -0.1700
Data Index: 4381367 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.2840. Min Act: -0.1700
Data Index: 19718 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.2840. Min Act: -0.1700
Data Index: 6278513 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.2528. Min Act: -0.1700
Data Index: 5949182 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.2840. Min Act: -0.1700
Data Index: 1642095 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.2840. Min Act: -0.1700
Data Index: 758096 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.2528. Min Act: -0.1700
Data Index: 2145894 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3778. Min Range: -4.3778
Max Act: 4.2528. Min Act: -0.1700
Data Index: 3114961 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19