Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2428 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.6534. Min Act: -0.1700
Data Index: 7199046 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.5083. Min Act: -0.1700
Data Index: 823229 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.4921. Min Act: -0.1700
Data Index: 823247 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.4597. Min Act: -0.1700
Data Index: 5031543 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.4759. Min Act: -0.1700
Data Index: 1692352 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.4597. Min Act: -0.1700
Data Index: 8706151 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.4434. Min Act: -0.1700
Data Index: 1633685 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.4271. Min Act: -0.1700
Data Index: 8375102 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.4434. Min Act: -0.1700
Data Index: 8288549 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.4108. Min Act: -0.1700
Data Index: 4490148 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.4271. Min Act: -0.1700
Data Index: 1829718 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.4271. Min Act: -0.1700
Data Index: 8213395 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.4108. Min Act: -0.1700
Data Index: 2830749 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.4108. Min Act: -0.1700
Data Index: 864 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.4108. Min Act: -0.1700
Data Index: 8368823 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.3945. Min Act: -0.1700
Data Index: 1218400 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.3945. Min Act: -0.1700
Data Index: 7616081 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.3782. Min Act: -0.1700
Data Index: 5440305 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.4108. Min Act: -0.1700
Data Index: 6411833 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6534. Min Range: -2.6534
Max Act: 2.3782. Min Act: -0.1700
Data Index: 4102448 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19