Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 96 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.4642. Min Act: -0.1700
Data Index: 6272934 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.4017. Min Act: -0.1700
Data Index: 1390218 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.3080. Min Act: -0.1700
Data Index: 8430953 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.2455. Min Act: -0.1700
Data Index: 3862471 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.2767. Min Act: -0.1700
Data Index: 7370480 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.2142. Min Act: -0.1700
Data Index: 3291543 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.2455. Min Act: -0.1700
Data Index: 7170981 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.2142. Min Act: -0.1700
Data Index: 5496347 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.1205. Min Act: -0.1700
Data Index: 4544423 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.0892. Min Act: -0.1700
Data Index: 6976966 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.0892. Min Act: -0.1700
Data Index: 6426700 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.0892. Min Act: -0.1700
Data Index: 4611141 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.0892. Min Act: -0.1700
Data Index: 5078727 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.0580. Min Act: -0.1700
Data Index: 7516811 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.0580. Min Act: -0.1700
Data Index: 8342082 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4642. Min Range: -6.4642
Max Act: 5.9955. Min Act: -0.1700
Data Index: 8509948 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4642. Min Range: -6.4642
Max Act: 5.9955. Min Act: -0.1700
Data Index: 8678323 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4642. Min Range: -6.4642
Max Act: 5.9642. Min Act: -0.1700
Data Index: 4222177 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4642. Min Range: -6.4642
Max Act: 5.9642. Min Act: -0.1700
Data Index: 4201767 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4642. Min Range: -6.4642
Max Act: 6.0267. Min Act: -0.1700
Data Index: 8297795 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19