Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1160 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.8147. Min Act: -0.1700
Data Index: 2533046 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.6585. Min Act: -0.1700
Data Index: 5509259 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5960. Min Act: -0.1700
Data Index: 3690883 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.6272. Min Act: -0.1700
Data Index: 3198023 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5960. Min Act: -0.1700
Data Index: 6958085 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5335. Min Act: -0.1700
Data Index: 6445567 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5335. Min Act: -0.1700
Data Index: 8469977 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5647. Min Act: -0.1700
Data Index: 4091830 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5022. Min Act: -0.1700
Data Index: 3858350 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4710. Min Act: -0.1700
Data Index: 2576833 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5335. Min Act: -0.1700
Data Index: 6926467 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4710. Min Act: -0.1700
Data Index: 2641578 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.5022. Min Act: -0.1700
Data Index: 353537 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4397. Min Act: -0.1700
Data Index: 6784214 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4397. Min Act: -0.1700
Data Index: 7817696 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4397. Min Act: -0.1700
Data Index: 2360662 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4397. Min Act: -0.1700
Data Index: 5928731 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.3772. Min Act: -0.1700
Data Index: 5678727 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4085. Min Act: -0.1700
Data Index: 6693302 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8147. Min Range: -5.8147
Max Act: 5.4397. Min Act: -0.1700
Data Index: 8494890 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19