Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3592 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.4611. Min Act: -0.1700
Data Index: 561186 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.4454. Min Act: -0.1700
Data Index: 1184035 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.4141. Min Act: -0.1700
Data Index: 8007467 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.3827. Min Act: -0.1700
Data Index: 1961072 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.3827. Min Act: -0.1700
Data Index: 161633 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.3670. Min Act: -0.1700
Data Index: 1961076 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.3670. Min Act: -0.1700
Data Index: 4054739 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.3670. Min Act: -0.1700
Data Index: 4398125 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.3670. Min Act: -0.1700
Data Index: 8072134 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.3513. Min Act: -0.1700
Data Index: 552692 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.3356. Min Act: -0.1700
Data Index: 5045540 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.3200. Min Act: -0.1700
Data Index: 8192202 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.3200. Min Act: -0.1700
Data Index: 5992745 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.3200. Min Act: -0.1700
Data Index: 1214317 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.3356. Min Act: -0.1700
Data Index: 2031345 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.3200. Min Act: -0.1700
Data Index: 7419800 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.2886. Min Act: -0.1700
Data Index: 957854 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.2886. Min Act: -0.1700
Data Index: 7646340 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.2886. Min Act: -0.1700
Data Index: 3640359 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4611. Min Range: -3.4611
Max Act: 3.2729. Min Act: -0.1700
Data Index: 6298567 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19