Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2312 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.6893. Min Act: -0.1700
Data Index: 5344325 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.5484. Min Act: -0.1700
Data Index: 7711310 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.5015. Min Act: -0.1700
Data Index: 2171155 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.4231. Min Act: -0.1700
Data Index: 1613803 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.4231. Min Act: -0.1700
Data Index: 4281213 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.3761. Min Act: -0.1700
Data Index: 5428262 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.3604. Min Act: -0.1700
Data Index: 1997831 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.3133. Min Act: -0.1700
Data Index: 4245603 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.2976. Min Act: -0.1700
Data Index: 7756647 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.2976. Min Act: -0.1700
Data Index: 6852297 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.2976. Min Act: -0.1700
Data Index: 1675811 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.2976. Min Act: -0.1700
Data Index: 7711314 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.2976. Min Act: -0.1700
Data Index: 5970828 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.2819. Min Act: -0.1700
Data Index: 876117 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.2819. Min Act: -0.1700
Data Index: 5267308 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.2819. Min Act: -0.1700
Data Index: 5814245 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.2662. Min Act: -0.1700
Data Index: 3161989 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.2505. Min Act: -0.1700
Data Index: 7508840 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.2505. Min Act: -0.1700
Data Index: 6861772 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6893. Min Range: -3.6893
Max Act: 3.2505. Min Act: -0.1700
Data Index: 8535425 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19