Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4403 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5143. Min Range: -5.5143
Max Act: 5.5143. Min Act: -0.1700
Data Index: 632093 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5143. Min Range: -5.5143
Max Act: 5.3581. Min Act: -0.1700
Data Index: 3575599 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5143. Min Range: -5.5143
Max Act: 5.3581. Min Act: -0.1700
Data Index: 882061 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5143. Min Range: -5.5143
Max Act: 5.2643. Min Act: -0.1700
Data Index: 4668835 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5143. Min Range: -5.5143
Max Act: 5.2018. Min Act: -0.1700
Data Index: 3394896 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5143. Min Range: -5.5143
Max Act: 5.1706. Min Act: -0.1700
Data Index: 4705572 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5143. Min Range: -5.5143
Max Act: 5.0768. Min Act: -0.1700
Data Index: 5885644 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5143. Min Range: -5.5143
Max Act: 5.0456. Min Act: -0.1700
Data Index: 7006990 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5143. Min Range: -5.5143
Max Act: 5.0143. Min Act: -0.1700
Data Index: 7730198 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5143. Min Range: -5.5143
Max Act: 5.0143. Min Act: -0.1700
Data Index: 991390 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5143. Min Range: -5.5143
Max Act: 4.9831. Min Act: -0.1700
Data Index: 7759068 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5143. Min Range: -5.5143
Max Act: 4.9831. Min Act: -0.1700
Data Index: 7821457 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5143. Min Range: -5.5143
Max Act: 4.9518. Min Act: -0.1700
Data Index: 834382 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5143. Min Range: -5.5143
Max Act: 4.9518. Min Act: -0.1700
Data Index: 7212084 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5143. Min Range: -5.5143
Max Act: 4.9518. Min Act: -0.1700
Data Index: 8626897 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5143. Min Range: -5.5143
Max Act: 4.9518. Min Act: -0.1700
Data Index: 6301777 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5143. Min Range: -5.5143
Max Act: 4.9518. Min Act: -0.1700
Data Index: 503732 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5143. Min Range: -5.5143
Max Act: 4.9206. Min Act: -0.1700
Data Index: 6281126 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5143. Min Range: -5.5143
Max Act: 4.9206. Min Act: -0.1700
Data Index: 4131334 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5143. Min Range: -5.5143
Max Act: 4.8893. Min Act: -0.1700
Data Index: 4242856 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19