Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3912 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.7940. Min Act: -0.1700
Data Index: 6236149 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.8253. Min Act: -0.1700
Data Index: 23056 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.7628. Min Act: -0.1700
Data Index: 462366 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.6690. Min Act: -0.1700
Data Index: 599324 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.6690. Min Act: -0.1700
Data Index: 6965892 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.6378. Min Act: -0.1700
Data Index: 3553727 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.6690. Min Act: -0.1700
Data Index: 8191740 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.5753. Min Act: -0.1700
Data Index: 7739887 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.5440. Min Act: -0.1700
Data Index: 862574 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.4815. Min Act: -0.1700
Data Index: 55072 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.4815. Min Act: -0.1700
Data Index: 710424 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.5128. Min Act: -0.1700
Data Index: 2668571 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.4815. Min Act: -0.1700
Data Index: 2755952 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.4815. Min Act: -0.1700
Data Index: 7223829 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.5128. Min Act: -0.1700
Data Index: 7731761 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.4815. Min Act: -0.1700
Data Index: 1165725 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.4815. Min Act: -0.1700
Data Index: 1255376 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.4815. Min Act: -0.1700
Data Index: 5856657 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.4815. Min Act: -0.1700
Data Index: 1801324 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8253. Min Range: -5.8253
Max Act: 5.4503. Min Act: -0.1700
Data Index: 3317711 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19