Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3121 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9131. Min Range: -6.9131
Max Act: 6.9131. Min Act: -0.1700
Data Index: 8589348 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9131. Min Range: -6.9131
Max Act: 6.5381. Min Act: -0.1700
Data Index: 7157236 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9131. Min Range: -6.9131
Max Act: 6.4756. Min Act: -0.1700
Data Index: 3004189 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9131. Min Range: -6.9131
Max Act: 6.1943. Min Act: -0.1700
Data Index: 3684334 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9131. Min Range: -6.9131
Max Act: 6.0693. Min Act: -0.1700
Data Index: 7653566 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9131. Min Range: -6.9131
Max Act: 6.0068. Min Act: -0.1700
Data Index: 3972017 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9131. Min Range: -6.9131
Max Act: 6.0068. Min Act: -0.1700
Data Index: 6988428 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9131. Min Range: -6.9131
Max Act: 5.9756. Min Act: -0.1700
Data Index: 3730701 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9131. Min Range: -6.9131
Max Act: 5.9756. Min Act: -0.1700
Data Index: 7992894 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9131. Min Range: -6.9131
Max Act: 5.9756. Min Act: -0.1700
Data Index: 7334037 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9131. Min Range: -6.9131
Max Act: 6.0068. Min Act: -0.1700
Data Index: 6709914 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9131. Min Range: -6.9131
Max Act: 5.8818. Min Act: -0.1700
Data Index: 3156663 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9131. Min Range: -6.9131
Max Act: 5.8818. Min Act: -0.1700
Data Index: 1908666 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9131. Min Range: -6.9131
Max Act: 5.9131. Min Act: -0.1700
Data Index: 2774196 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9131. Min Range: -6.9131
Max Act: 5.8506. Min Act: -0.1700
Data Index: 4726061 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9131. Min Range: -6.9131
Max Act: 5.8818. Min Act: -0.1700
Data Index: 1259051 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9131. Min Range: -6.9131
Max Act: 5.8193. Min Act: -0.1700
Data Index: 2941593 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9131. Min Range: -6.9131
Max Act: 5.8506. Min Act: -0.1700
Data Index: 2517901 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9131. Min Range: -6.9131
Max Act: 5.8193. Min Act: -0.1700
Data Index: 1995602 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9131. Min Range: -6.9131
Max Act: 5.8193. Min Act: -0.1700
Data Index: 7304973 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19