Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3148 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.9960. Min Act: -0.1700
Data Index: 1817612 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.9335. Min Act: -0.1700
Data Index: 1976196 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.9335. Min Act: -0.1700
Data Index: 7746243 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.9022. Min Act: -0.1700
Data Index: 1881337 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.8710. Min Act: -0.1700
Data Index: 6972353 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.8710. Min Act: -0.1700
Data Index: 4467132 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.8085. Min Act: -0.1700
Data Index: 8525108 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7772. Min Act: -0.1700
Data Index: 2218322 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7772. Min Act: -0.1700
Data Index: 6713292 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7460. Min Act: -0.1700
Data Index: 3021008 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7460. Min Act: -0.1700
Data Index: 3536148 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7460. Min Act: -0.1700
Data Index: 2267683 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7460. Min Act: -0.1700
Data Index: 6100557 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7147. Min Act: -0.1700
Data Index: 6398097 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7147. Min Act: -0.1700
Data Index: 5886668 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7147. Min Act: -0.1700
Data Index: 6390121 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.7147. Min Act: -0.1700
Data Index: 6970783 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.6835. Min Act: -0.1700
Data Index: 2204444 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.6522. Min Act: -0.1700
Data Index: 7361965 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9960. Min Range: -5.9960
Max Act: 5.6522. Min Act: -0.1700
Data Index: 5295418 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19