Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3467 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0221. Min Range: -7.0221
Max Act: 7.0221. Min Act: -0.1700
Data Index: 3147654 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.8346. Min Act: -0.1700
Data Index: 2076127 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.7408. Min Act: -0.1700
Data Index: 8135851 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.6783. Min Act: -0.1700
Data Index: 6925615 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.6158. Min Act: -0.1700
Data Index: 8086294 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.5846. Min Act: -0.1700
Data Index: 7571132 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.5221. Min Act: -0.1700
Data Index: 1568049 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.4908. Min Act: -0.1700
Data Index: 6568213 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.4908. Min Act: -0.1700
Data Index: 2089246 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.4908. Min Act: -0.1700
Data Index: 8004670 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.4596. Min Act: -0.1700
Data Index: 2365322 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.4596. Min Act: -0.1700
Data Index: 3980160 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.4283. Min Act: -0.1700
Data Index: 6283566 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.4283. Min Act: -0.1700
Data Index: 5106011 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.3346. Min Act: -0.1700
Data Index: 5555460 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.3033. Min Act: -0.1700
Data Index: 8285430 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.3033. Min Act: -0.1700
Data Index: 3787738 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.3033. Min Act: -0.1700
Data Index: 7771368 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.3033. Min Act: -0.1700
Data Index: 38986 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0221. Min Range: -7.0221
Max Act: 6.2721. Min Act: -0.1700
Data Index: 2252295 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19