Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1488. Min Range: -4.1488
Max Act: 4.1488. Min Act: -0.1700
Data Index: 1233367 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1488. Min Range: -4.1488
Max Act: 4.0863. Min Act: -0.1700
Data Index: 2264937 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1488. Min Range: -4.1488
Max Act: 4.0551. Min Act: -0.1700
Data Index: 7150362 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.9925. Min Act: -0.1699
Data Index: 1708977 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.9925. Min Act: -0.1700
Data Index: 4081567 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.9300. Min Act: -0.1700
Data Index: 2696782 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.9300. Min Act: -0.1700
Data Index: 7077274 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.8987. Min Act: -0.1700
Data Index: 1303445 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.8987. Min Act: -0.1700
Data Index: 7199716 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.8675. Min Act: -0.1700
Data Index: 3247295 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.8987. Min Act: -0.1700
Data Index: 1041754 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.8987. Min Act: -0.1700
Data Index: 3170961 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.8675. Min Act: -0.1700
Data Index: 5702365 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.8675. Min Act: -0.1700
Data Index: 1806134 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.8675. Min Act: -0.1700
Data Index: 6181713 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.8675. Min Act: -0.1700
Data Index: 3432653 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.8675. Min Act: -0.1700
Data Index: 7145549 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.8675. Min Act: -0.1700
Data Index: 2538796 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.8987. Min Act: -0.1700
Data Index: 3116277 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1488. Min Range: -4.1488
Max Act: 3.8675. Min Act: -0.1700
Data Index: 7331584 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19