Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4377 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.6487. Min Act: -0.1700
Data Index: 794930 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.5522. Min Act: -0.1700
Data Index: 4900205 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.5360. Min Act: -0.1700
Data Index: 1432900 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.5360. Min Act: -0.1700
Data Index: 2470742 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.5036. Min Act: -0.1700
Data Index: 6974103 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.5036. Min Act: -0.1700
Data Index: 6393223 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.4874. Min Act: -0.1700
Data Index: 3717231 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.5036. Min Act: -0.1700
Data Index: 2470178 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.5036. Min Act: -0.1700
Data Index: 4920945 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.4874. Min Act: -0.1700
Data Index: 729757 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.4874. Min Act: -0.1699
Data Index: 6788914 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.4874. Min Act: -0.1700
Data Index: 3704176 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.4712. Min Act: -0.1700
Data Index: 8292159 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.4550. Min Act: -0.1700
Data Index: 8291788 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.4712. Min Act: -0.1700
Data Index: 1722305 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.4874. Min Act: -0.1700
Data Index: 4923289 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.4712. Min Act: -0.1700
Data Index: 8427941 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.4712. Min Act: -0.1700
Data Index: 8425956 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.4712. Min Act: -0.1700
Data Index: 5344373 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6487. Min Range: -2.6487
Max Act: 2.4387. Min Act: -0.1700
Data Index: 8412790 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19