Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3694 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2215. Min Range: -4.2215
Max Act: 4.2215. Min Act: -0.1700
Data Index: 4768089 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2215. Min Range: -4.2215
Max Act: 4.1278. Min Act: -0.1700
Data Index: 2292633 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2215. Min Range: -4.2215
Max Act: 4.0653. Min Act: -0.1700
Data Index: 6475464 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2215. Min Range: -4.2215
Max Act: 4.0340. Min Act: -0.1700
Data Index: 19815 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2215. Min Range: -4.2215
Max Act: 4.0027. Min Act: -0.1700
Data Index: 3488077 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2215. Min Range: -4.2215
Max Act: 4.0027. Min Act: -0.1700
Data Index: 2971751 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2215. Min Range: -4.2215
Max Act: 3.9402. Min Act: -0.1700
Data Index: 2401956 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2215. Min Range: -4.2215
Max Act: 3.9246. Min Act: -0.1700
Data Index: 5231688 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2215. Min Range: -4.2215
Max Act: 3.9090. Min Act: -0.1700
Data Index: 7189318 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2215. Min Range: -4.2215
Max Act: 3.9246. Min Act: -0.1700
Data Index: 534362 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2215. Min Range: -4.2215
Max Act: 3.9090. Min Act: -0.1700
Data Index: 8408295 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2215. Min Range: -4.2215
Max Act: 3.9090. Min Act: -0.1700
Data Index: 6050344 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2215. Min Range: -4.2215
Max Act: 3.8933. Min Act: -0.1700
Data Index: 3352388 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2215. Min Range: -4.2215
Max Act: 3.8933. Min Act: -0.1700
Data Index: 8082939 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2215. Min Range: -4.2215
Max Act: 3.8933. Min Act: -0.1700
Data Index: 793856 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2215. Min Range: -4.2215
Max Act: 3.8933. Min Act: -0.1700
Data Index: 2905625 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2215. Min Range: -4.2215
Max Act: 3.8777. Min Act: -0.1700
Data Index: 2690910 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2215. Min Range: -4.2215
Max Act: 3.8777. Min Act: -0.1700
Data Index: 5293193 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2215. Min Range: -4.2215
Max Act: 3.8777. Min Act: -0.1700
Data Index: 3281893 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2215. Min Range: -4.2215
Max Act: 3.8464. Min Act: -0.1700
Data Index: 5780861 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19