Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 94 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1964. Min Range: -7.1964
Max Act: 7.1964. Min Act: -0.1700
Data Index: 8014620 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1964. Min Range: -7.1964
Max Act: 7.1339. Min Act: -0.1700
Data Index: 3428092 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1964. Min Range: -7.1964
Max Act: 7.0714. Min Act: -0.1700
Data Index: 3463313 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1964. Min Range: -7.1964
Max Act: 7.0401. Min Act: -0.1700
Data Index: 4784351 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1964. Min Range: -7.1964
Max Act: 7.0089. Min Act: -0.1700
Data Index: 740324 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1964. Min Range: -7.1964
Max Act: 6.9776. Min Act: -0.1700
Data Index: 636842 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1964. Min Range: -7.1964
Max Act: 7.0089. Min Act: -0.1700
Data Index: 5045511 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1964. Min Range: -7.1964
Max Act: 6.9776. Min Act: -0.1700
Data Index: 6825228 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1964. Min Range: -7.1964
Max Act: 6.9151. Min Act: -0.1700
Data Index: 304324 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1964. Min Range: -7.1964
Max Act: 6.9464. Min Act: -0.1700
Data Index: 8018752 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1964. Min Range: -7.1964
Max Act: 6.9151. Min Act: -0.1700
Data Index: 2774877 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1964. Min Range: -7.1964
Max Act: 6.9464. Min Act: -0.1700
Data Index: 8261297 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1964. Min Range: -7.1964
Max Act: 6.8839. Min Act: -0.1700
Data Index: 1423003 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1964. Min Range: -7.1964
Max Act: 6.8839. Min Act: -0.1700
Data Index: 7290268 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1964. Min Range: -7.1964
Max Act: 6.8526. Min Act: -0.1700
Data Index: 6459065 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1964. Min Range: -7.1964
Max Act: 6.8214. Min Act: -0.1700
Data Index: 7947374 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1964. Min Range: -7.1964
Max Act: 6.7901. Min Act: -0.1700
Data Index: 3476182 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1964. Min Range: -7.1964
Max Act: 6.8214. Min Act: -0.1700
Data Index: 1317033 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1964. Min Range: -7.1964
Max Act: 6.7901. Min Act: -0.1700
Data Index: 2544795 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1964. Min Range: -7.1964
Max Act: 6.7901. Min Act: -0.1700
Data Index: 6066731 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19