Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 649 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0025. Min Range: -7.0025
Max Act: 7.0025. Min Act: -0.1700
Data Index: 6581850 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.9400. Min Act: -0.1700
Data Index: 812988 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.8775. Min Act: -0.1700
Data Index: 6393070 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.8775. Min Act: -0.1700
Data Index: 4218557 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.8463. Min Act: -0.1700
Data Index: 3206568 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.8150. Min Act: -0.1700
Data Index: 7814116 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.7838. Min Act: -0.1700
Data Index: 3099093 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.7525. Min Act: -0.1700
Data Index: 4282492 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.7213. Min Act: -0.1700
Data Index: 7870430 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.6588. Min Act: -0.1700
Data Index: 6451977 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.6588. Min Act: -0.1700
Data Index: 2185731 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.6588. Min Act: -0.1700
Data Index: 2452036 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.6275. Min Act: -0.1700
Data Index: 1935584 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.6275. Min Act: -0.1700
Data Index: 6689592 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.6275. Min Act: -0.1700
Data Index: 7892184 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.5963. Min Act: -0.1700
Data Index: 7423887 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.6275. Min Act: -0.1700
Data Index: 1294269 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.5650. Min Act: -0.1700
Data Index: 1289596 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.5650. Min Act: -0.1700
Data Index: 2239609 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0025. Min Range: -7.0025
Max Act: 6.5650. Min Act: -0.1700
Data Index: 796279 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19