Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 733 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.8086. Min Act: -0.1700
Data Index: 4307323 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.7914. Min Act: -0.1700
Data Index: 8305050 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.7310. Min Act: -0.1697
Data Index: 6061713 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.7223. Min Act: -0.1661
Data Index: 2434775 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.7137. Min Act: -0.1700
Data Index: 4130955 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.6963. Min Act: -0.1700
Data Index: 2553303 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.7050. Min Act: -0.1695
Data Index: 6185913 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.6790. Min Act: -0.1700
Data Index: 7320360 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.6703. Min Act: -0.1700
Data Index: 161860 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.6703. Min Act: -0.1700
Data Index: 2770537 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.6616. Min Act: -0.1700
Data Index: 4646573 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.6616. Min Act: -0.1699
Data Index: 3179105 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.6616. Min Act: -0.1700
Data Index: 667813 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.6529. Min Act: -0.1700
Data Index: 6336439 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.6529. Min Act: -0.1699
Data Index: 5778175 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.6442. Min Act: -0.1700
Data Index: 1500856 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.6529. Min Act: -0.1697
Data Index: 8406719 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.6442. Min Act: -0.1700
Data Index: 5033351 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.6442. Min Act: -0.1700
Data Index: 1144570 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8086. Min Range: -1.8086
Max Act: 1.6355. Min Act: -0.1700
Data Index: 2192425 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19