Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 138 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.9507. Min Act: -0.1700
Data Index: 4277541 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.8569. Min Act: -0.1700
Data Index: 4490749 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.6694. Min Act: -0.1700
Data Index: 3972378 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.5444. Min Act: -0.1700
Data Index: 1904314 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.4507. Min Act: -0.1700
Data Index: 2739900 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.4507. Min Act: -0.1700
Data Index: 7283058 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.4194. Min Act: -0.1700
Data Index: 5075567 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.4194. Min Act: -0.1700
Data Index: 3766242 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.4507. Min Act: -0.1699
Data Index: 1559768 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.3882. Min Act: -0.1700
Data Index: 5709189 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.3569. Min Act: -0.1700
Data Index: 2829719 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.3257. Min Act: -0.1700
Data Index: 2829720 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.2632. Min Act: -0.1700
Data Index: 5749285 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.2944. Min Act: -0.1700
Data Index: 2446731 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.2632. Min Act: -0.1700
Data Index: 4714300 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.2319. Min Act: -0.1700
Data Index: 4490750 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.2319. Min Act: -0.1700
Data Index: 611253 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.2007. Min Act: -0.1700
Data Index: 797844 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.2319. Min Act: -0.1700
Data Index: 5733812 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9507. Min Range: -6.9507
Max Act: 6.2319. Min Act: -0.1700
Data Index: 7457365 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19