Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.7225. Min Act: -0.1700
Data Index: 867558 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6443. Min Act: -0.1700
Data Index: 8211038 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.6443. Min Act: -0.1700
Data Index: 3926582 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.5660. Min Act: -0.1700
Data Index: 4390224 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.5191. Min Act: -0.1700
Data Index: 7874463 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.5347. Min Act: -0.1700
Data Index: 970672 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.5191. Min Act: -0.1700
Data Index: 6949459 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.4721. Min Act: -0.1700
Data Index: 6519042 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.4721. Min Act: -0.1700
Data Index: 6575114 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.4564. Min Act: -0.1700
Data Index: 713970 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.4564. Min Act: -0.1700
Data Index: 5739906 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.4564. Min Act: -0.1700
Data Index: 5126023 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.4564. Min Act: -0.1700
Data Index: 5751935 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.4251. Min Act: -0.1700
Data Index: 4259068 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.4251. Min Act: -0.1700
Data Index: 50473 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.4251. Min Act: -0.1700
Data Index: 1988584 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.4094. Min Act: -0.1700
Data Index: 7479687 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.3937. Min Act: -0.1700
Data Index: 867818 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.3623. Min Act: -0.1700
Data Index: 4425612 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7225. Min Range: -3.7225
Max Act: 3.3780. Min Act: -0.1700
Data Index: 1343967 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19