Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 604 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.8206. Min Act: -0.1700
Data Index: 1421550 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.3206. Min Act: -0.1700
Data Index: 3497135 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.2893. Min Act: -0.1700
Data Index: 4136911 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.2893. Min Act: -0.1700
Data Index: 558777 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.2893. Min Act: -0.1700
Data Index: 5620500 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.2268. Min Act: -0.1700
Data Index: 2782263 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.2268. Min Act: -0.1700
Data Index: 7454155 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.2581. Min Act: -0.1700
Data Index: 8063687 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.1956. Min Act: -0.1700
Data Index: 2337517 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.1956. Min Act: -0.1700
Data Index: 4023728 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.1643. Min Act: -0.1700
Data Index: 8164424 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.1331. Min Act: -0.1700
Data Index: 6657244 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.1331. Min Act: -0.1700
Data Index: 2984425 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.1331. Min Act: -0.1700
Data Index: 7632452 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.1018. Min Act: -0.1700
Data Index: 5686068 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.0706. Min Act: -0.1700
Data Index: 6433933 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.0393. Min Act: -0.1700
Data Index: 5402884 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.0706. Min Act: -0.1700
Data Index: 1316187 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.0081. Min Act: -0.1700
Data Index: 7673894 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8206. Min Range: -6.8206
Max Act: 6.0706. Min Act: -0.1700
Data Index: 866304 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19