Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5695. Min Range: -7.5695
Max Act: 7.5695. Min Act: -0.1700
Data Index: 5716838 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5695. Min Range: -7.5695
Max Act: 7.1008. Min Act: -0.1700
Data Index: 6413384 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5695. Min Range: -7.5695
Max Act: 7.1008. Min Act: -0.1700
Data Index: 7675256 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5695. Min Range: -7.5695
Max Act: 7.0070. Min Act: -0.1700
Data Index: 5077871 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5695. Min Range: -7.5695
Max Act: 7.0383. Min Act: -0.1700
Data Index: 3334455 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5695. Min Range: -7.5695
Max Act: 7.0070. Min Act: -0.1700
Data Index: 5063070 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5695. Min Range: -7.5695
Max Act: 6.9445. Min Act: -0.1700
Data Index: 5716841 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5695. Min Range: -7.5695
Max Act: 6.9445. Min Act: -0.1700
Data Index: 1798194 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5695. Min Range: -7.5695
Max Act: 6.9758. Min Act: -0.1700
Data Index: 5462132 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5695. Min Range: -7.5695
Max Act: 6.9445. Min Act: -0.1700
Data Index: 3737780 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5695. Min Range: -7.5695
Max Act: 6.9133. Min Act: -0.1700
Data Index: 4775441 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5695. Min Range: -7.5695
Max Act: 6.9445. Min Act: -0.1700
Data Index: 3239698 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5695. Min Range: -7.5695
Max Act: 6.8508. Min Act: -0.1700
Data Index: 6103576 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5695. Min Range: -7.5695
Max Act: 6.8195. Min Act: -0.1700
Data Index: 3373160 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5695. Min Range: -7.5695
Max Act: 6.8508. Min Act: -0.1700
Data Index: 543522 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5695. Min Range: -7.5695
Max Act: 6.8195. Min Act: -0.1700
Data Index: 4088841 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5695. Min Range: -7.5695
Max Act: 6.7883. Min Act: -0.1700
Data Index: 4265255 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5695. Min Range: -7.5695
Max Act: 6.7883. Min Act: -0.1700
Data Index: 3337057 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5695. Min Range: -7.5695
Max Act: 6.7883. Min Act: -0.1700
Data Index: 2468910 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5695. Min Range: -7.5695
Max Act: 6.7883. Min Act: -0.1700
Data Index: 7546901 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19