Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3121 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.9526. Min Act: -0.1700
Data Index: 2787869 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.5151. Min Act: -0.1700
Data Index: 39495 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.5151. Min Act: -0.1700
Data Index: 7258631 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.3901. Min Act: -0.1700
Data Index: 4901056 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.3901. Min Act: -0.1700
Data Index: 2304509 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.3276. Min Act: -0.1700
Data Index: 8549394 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.3276. Min Act: -0.1700
Data Index: 6709197 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.3276. Min Act: -0.1700
Data Index: 5515920 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.3276. Min Act: -0.1700
Data Index: 4184209 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.2651. Min Act: -0.1700
Data Index: 2881159 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.2651. Min Act: -0.1700
Data Index: 7947237 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.2651. Min Act: -0.1700
Data Index: 1404023 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.2026. Min Act: -0.1700
Data Index: 3244449 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.2026. Min Act: -0.1700
Data Index: 5638038 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.2026. Min Act: -0.1700
Data Index: 7894432 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.2026. Min Act: -0.1700
Data Index: 4076984 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.1401. Min Act: -0.1700
Data Index: 1839292 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.1401. Min Act: -0.1700
Data Index: 752741 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.0151. Min Act: -0.1700
Data Index: 2147446 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9526. Min Range: -8.9526
Max Act: 8.0776. Min Act: -0.1700
Data Index: 5460666 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19