Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3212 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9506. Min Range: -6.9506
Max Act: 6.9506. Min Act: -0.1700
Data Index: 7845315 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9506. Min Range: -6.9506
Max Act: 6.6381. Min Act: -0.1700
Data Index: 6889241 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9506. Min Range: -6.9506
Max Act: 6.5131. Min Act: -0.1700
Data Index: 7910850 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9506. Min Range: -6.9506
Max Act: 6.3256. Min Act: -0.1700
Data Index: 375124 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9506. Min Range: -6.9506
Max Act: 6.2943. Min Act: -0.1700
Data Index: 1010569 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9506. Min Range: -6.9506
Max Act: 6.0443. Min Act: -0.1700
Data Index: 1816341 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9506. Min Range: -6.9506
Max Act: 5.9506. Min Act: -0.1700
Data Index: 611950 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9506. Min Range: -6.9506
Max Act: 5.9506. Min Act: -0.1700
Data Index: 1932159 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9506. Min Range: -6.9506
Max Act: 5.9506. Min Act: -0.1700
Data Index: 3072550 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9506. Min Range: -6.9506
Max Act: 5.9193. Min Act: -0.1700
Data Index: 2287783 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9506. Min Range: -6.9506
Max Act: 5.9193. Min Act: -0.1700
Data Index: 1234331 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9506. Min Range: -6.9506
Max Act: 5.9193. Min Act: -0.1700
Data Index: 7700489 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9506. Min Range: -6.9506
Max Act: 5.9193. Min Act: -0.1700
Data Index: 6293822 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9506. Min Range: -6.9506
Max Act: 5.9193. Min Act: -0.1700
Data Index: 6540758 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9506. Min Range: -6.9506
Max Act: 5.8881. Min Act: -0.1700
Data Index: 25236 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9506. Min Range: -6.9506
Max Act: 5.8568. Min Act: -0.1700
Data Index: 8188719 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9506. Min Range: -6.9506
Max Act: 5.8568. Min Act: -0.1700
Data Index: 2483532 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9506. Min Range: -6.9506
Max Act: 5.8568. Min Act: -0.1700
Data Index: 501618 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9506. Min Range: -6.9506
Max Act: 5.8256. Min Act: -0.1700
Data Index: 5550237 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9506. Min Range: -6.9506
Max Act: 5.8256. Min Act: -0.1700
Data Index: 4627885 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19