Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2091 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.5503. Min Act: -0.1700
Data Index: 4266574 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.4565. Min Act: -0.1700
Data Index: 3397238 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.4565. Min Act: -0.1700
Data Index: 3579712 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.4253. Min Act: -0.1700
Data Index: 8725583 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.3940. Min Act: -0.1700
Data Index: 343614 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.3628. Min Act: -0.1700
Data Index: 8611251 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.3003. Min Act: -0.1700
Data Index: 780951 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.3003. Min Act: -0.1700
Data Index: 6209766 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.2690. Min Act: -0.1700
Data Index: 3671225 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.2065. Min Act: -0.1700
Data Index: 21369 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.2378. Min Act: -0.1700
Data Index: 4011519 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.2065. Min Act: -0.1700
Data Index: 5141498 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.2065. Min Act: -0.1700
Data Index: 422080 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.2065. Min Act: -0.1700
Data Index: 8042980 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.2065. Min Act: -0.1700
Data Index: 805095 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.1753. Min Act: -0.1700
Data Index: 2754300 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.1753. Min Act: -0.1700
Data Index: 4741998 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.1440. Min Act: -0.1700
Data Index: 4445034 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.1753. Min Act: -0.1700
Data Index: 1495151 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5503. Min Range: -6.5503
Max Act: 6.1440. Min Act: -0.1700
Data Index: 3107370 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19