Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1270 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0557. Min Range: -5.0557
Max Act: 5.0557. Min Act: -0.1700
Data Index: 2022332 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0557. Min Range: -5.0557
Max Act: 5.0244. Min Act: -0.1700
Data Index: 103774 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9932. Min Act: -0.1700
Data Index: 4694556 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9932. Min Act: -0.1700
Data Index: 4928732 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9619. Min Act: -0.1700
Data Index: 4914181 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9307. Min Act: -0.1700
Data Index: 3661592 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9307. Min Act: -0.1700
Data Index: 5235906 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.8994. Min Act: -0.1700
Data Index: 7287548 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.8369. Min Act: -0.1700
Data Index: 5500334 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.8682. Min Act: -0.1700
Data Index: 1178600 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.8369. Min Act: -0.1700
Data Index: 5216171 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.8682. Min Act: -0.1700
Data Index: 865583 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.8057. Min Act: -0.1700
Data Index: 5170167 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.7432. Min Act: -0.1700
Data Index: 6810055 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.7744. Min Act: -0.1700
Data Index: 5052549 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.8057. Min Act: -0.1700
Data Index: 4149040 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.7432. Min Act: -0.1700
Data Index: 4390669 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.7432. Min Act: -0.1700
Data Index: 4723742 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.7119. Min Act: -0.1700
Data Index: 1417514 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.7119. Min Act: -0.1700
Data Index: 7493743 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19