Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4962 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.9873. Min Act: -0.1700
Data Index: 3431419 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.9561. Min Act: -0.1700
Data Index: 6417810 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.8623. Min Act: -0.1700
Data Index: 3070711 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.7998. Min Act: -0.1700
Data Index: 8078999 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.7998. Min Act: -0.1700
Data Index: 5924811 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.7998. Min Act: -0.1700
Data Index: 7440731 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.7061. Min Act: -0.1700
Data Index: 5272622 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.6748. Min Act: -0.1700
Data Index: 669941 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.6748. Min Act: -0.1700
Data Index: 6555167 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.6436. Min Act: -0.1700
Data Index: 4455677 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.6436. Min Act: -0.1700
Data Index: 185301 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.6436. Min Act: -0.1700
Data Index: 7376168 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.6123. Min Act: -0.1700
Data Index: 6364003 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.5498. Min Act: -0.1700
Data Index: 1132696 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.5498. Min Act: -0.1700
Data Index: 2864108 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.5186. Min Act: -0.1700
Data Index: 6928129 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.5498. Min Act: -0.1700
Data Index: 3435035 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.4873. Min Act: -0.1700
Data Index: 3848081 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.4873. Min Act: -0.1700
Data Index: 1331713 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9873. Min Range: -5.9873
Max Act: 5.4561. Min Act: -0.1700
Data Index: 6700690 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19