Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2774 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0261. Min Range: -5.0261
Max Act: 5.0261. Min Act: -0.1700
Data Index: 7668490 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.8699. Min Act: -0.1700
Data Index: 694581 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.8074. Min Act: -0.1700
Data Index: 5091811 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.7761. Min Act: -0.1700
Data Index: 5636368 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.7136. Min Act: -0.1700
Data Index: 1214323 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.7136. Min Act: -0.1700
Data Index: 1712516 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.5261. Min Act: -0.1700
Data Index: 5976406 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.4949. Min Act: -0.1700
Data Index: 8691349 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.4636. Min Act: -0.1700
Data Index: 1585384 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.4324. Min Act: -0.1696
Data Index: 7616736 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.4636. Min Act: -0.1700
Data Index: 7392119 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.4011. Min Act: -0.1700
Data Index: 563712 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.4011. Min Act: -0.1700
Data Index: 8679713 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.3699. Min Act: -0.1700
Data Index: 7463621 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.3699. Min Act: -0.1700
Data Index: 7709133 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.3386. Min Act: -0.1700
Data Index: 2961947 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.3386. Min Act: -0.1700
Data Index: 3655122 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.3386. Min Act: -0.1700
Data Index: 1303091 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.3386. Min Act: -0.1700
Data Index: 1515697 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0261. Min Range: -5.0261
Max Act: 4.3386. Min Act: -0.1700
Data Index: 7448262 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19