Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.9554. Min Act: -0.1700
Data Index: 3016030 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.8304. Min Act: -0.1700
Data Index: 865981 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.7991. Min Act: -0.1700
Data Index: 2576650 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.7991. Min Act: -0.1700
Data Index: 7310914 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.7366. Min Act: -0.1700
Data Index: 7749770 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6741. Min Act: -0.1700
Data Index: 6841728 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6741. Min Act: -0.1700
Data Index: 4817259 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6429. Min Act: -0.1700
Data Index: 2362459 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6116. Min Act: -0.1700
Data Index: 1985216 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6429. Min Act: -0.1700
Data Index: 4987967 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5491. Min Act: -0.1700
Data Index: 8705631 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5491. Min Act: -0.1700
Data Index: 7926601 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5179. Min Act: -0.1700
Data Index: 8163254 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4866. Min Act: -0.1700
Data Index: 2350456 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4554. Min Act: -0.1700
Data Index: 3101602 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4554. Min Act: -0.1700
Data Index: 8608678 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4554. Min Act: -0.1700
Data Index: 4516137 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4866. Min Act: -0.1700
Data Index: 3749655 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4554. Min Act: -0.1700
Data Index: 8820114 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4554. Min Act: -0.1700
Data Index: 1727296 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19