Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.3781. Min Act: -0.1700
Data Index: 132740 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.3467. Min Act: -0.1700
Data Index: 4205987 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.3467. Min Act: -0.1700
Data Index: 8190042 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.3467. Min Act: -0.1700
Data Index: 3319914 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.3310. Min Act: -0.1700
Data Index: 8290500 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.3153. Min Act: -0.1700
Data Index: 1089660 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.2996. Min Act: -0.1700
Data Index: 8209259 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.2839. Min Act: -0.1700
Data Index: 7507463 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.3153. Min Act: -0.1700
Data Index: 2748191 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.2996. Min Act: -0.1700
Data Index: 3089115 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.2839. Min Act: -0.1700
Data Index: 3622308 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.2525. Min Act: -0.1700
Data Index: 4444481 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.2996. Min Act: -0.1700
Data Index: 2342324 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.2525. Min Act: -0.1700
Data Index: 4033283 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.2525. Min Act: -0.1700
Data Index: 3346907 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.2525. Min Act: -0.1700
Data Index: 4589564 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.2525. Min Act: -0.1700
Data Index: 3864943 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.2368. Min Act: -0.1700
Data Index: 3810503 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.2682. Min Act: -0.1700
Data Index: 3311426 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3781. Min Range: -3.3781
Max Act: 3.2525. Min Act: -0.1700
Data Index: 6136192 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19