Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 524 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.7612. Min Act: -0.1700
Data Index: 5832401 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.6987. Min Act: -0.1700
Data Index: 989986 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.6362. Min Act: -0.1700
Data Index: 3142306 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.6362. Min Act: -0.1700
Data Index: 6364569 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.5737. Min Act: -0.1700
Data Index: 3475474 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.6362. Min Act: -0.1700
Data Index: 7089602 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.4799. Min Act: -0.1700
Data Index: 6558671 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.4487. Min Act: -0.1700
Data Index: 8414052 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.4799. Min Act: -0.1700
Data Index: 3001990 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.4799. Min Act: -0.1700
Data Index: 4192315 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.4799. Min Act: -0.1700
Data Index: 6126548 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.5112. Min Act: -0.1700
Data Index: 7300799 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.4799. Min Act: -0.1700
Data Index: 1312967 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.4487. Min Act: -0.1700
Data Index: 1561224 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.4174. Min Act: -0.1700
Data Index: 2639524 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.3862. Min Act: -0.1700
Data Index: 2429179 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.3237. Min Act: -0.1700
Data Index: 6417416 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.3237. Min Act: -0.1700
Data Index: 2898541 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.3549. Min Act: -0.1700
Data Index: 2935879 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7612. Min Range: -4.7612
Max Act: 4.3862. Min Act: -0.1700
Data Index: 6547235 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19