Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1031. Min Range: -5.1031
Max Act: 5.1031. Min Act: -0.1700
Data Index: 7858055 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1031. Min Range: -5.1031
Max Act: 5.0719. Min Act: -0.1700
Data Index: 5222028 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1031. Min Range: -5.1031
Max Act: 5.0094. Min Act: -0.1700
Data Index: 7284729 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1031. Min Range: -5.1031
Max Act: 5.0094. Min Act: -0.1700
Data Index: 5595521 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1031. Min Range: -5.1031
Max Act: 5.0094. Min Act: -0.1700
Data Index: 2886337 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.9781. Min Act: -0.1700
Data Index: 2514864 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.9781. Min Act: -0.1700
Data Index: 180321 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.9781. Min Act: -0.1700
Data Index: 1235183 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.9469. Min Act: -0.1700
Data Index: 5413261 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.9469. Min Act: -0.1700
Data Index: 267305 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.9156. Min Act: -0.1700
Data Index: 2017242 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.9156. Min Act: -0.1700
Data Index: 4487582 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.9156. Min Act: -0.1700
Data Index: 8138885 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.8844. Min Act: -0.1700
Data Index: 2896963 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.8844. Min Act: -0.1700
Data Index: 733776 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.8844. Min Act: -0.1700
Data Index: 267304 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.8844. Min Act: -0.1700
Data Index: 6050540 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.8531. Min Act: -0.1700
Data Index: 1990669 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.8531. Min Act: -0.1700
Data Index: 4861677 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1031. Min Range: -5.1031
Max Act: 4.8531. Min Act: -0.1700
Data Index: 4515612 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19