Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3048 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.2702. Min Act: -0.1700
Data Index: 1034108 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.2545. Min Act: -0.1700
Data Index: 4019078 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.2388. Min Act: -0.1700
Data Index: 1034109 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.2073. Min Act: -0.1700
Data Index: 1034110 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.1444. Min Act: -0.1700
Data Index: 3046117 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.1286. Min Act: -0.1700
Data Index: 4033045 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0971. Min Act: -0.1700
Data Index: 1119206 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0814. Min Act: -0.1700
Data Index: 7479236 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0498. Min Act: -0.1700
Data Index: 5628377 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0656. Min Act: -0.1700
Data Index: 5667591 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0340. Min Act: -0.1700
Data Index: 588570 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0182. Min Act: -0.1700
Data Index: 2952392 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0340. Min Act: -0.1700
Data Index: 4598496 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0182. Min Act: -0.1700
Data Index: 8672270 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0024. Min Act: -0.1700
Data Index: 3646849 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0340. Min Act: -0.1700
Data Index: 1232217 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0024. Min Act: -0.1700
Data Index: 4707154 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2702. Min Range: -3.2702
Max Act: 3.0024. Min Act: -0.1700
Data Index: 3840703 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2702. Min Range: -3.2702
Max Act: 2.9866. Min Act: -0.1700
Data Index: 2414608 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2702. Min Range: -3.2702
Max Act: 2.9866. Min Act: -0.1700
Data Index: 459094 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19