Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4405 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.3862. Min Act: -0.1700
Data Index: 4591419 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.3237. Min Act: -0.1700
Data Index: 6974983 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.3237. Min Act: -0.1700
Data Index: 3211464 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.2612. Min Act: -0.1700
Data Index: 3713030 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.2612. Min Act: -0.1700
Data Index: 8241710 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.2300. Min Act: -0.1700
Data Index: 1042464 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.2612. Min Act: -0.1700
Data Index: 835948 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.2300. Min Act: -0.1700
Data Index: 1143459 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.2300. Min Act: -0.1700
Data Index: 2171457 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.1675. Min Act: -0.1700
Data Index: 6378481 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.1675. Min Act: -0.1700
Data Index: 3342048 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.1050. Min Act: -0.1700
Data Index: 8468192 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.1362. Min Act: -0.1700
Data Index: 2844284 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.1050. Min Act: -0.1700
Data Index: 1073868 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.0737. Min Act: -0.1700
Data Index: 4338541 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.0737. Min Act: -0.1700
Data Index: 4061975 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.1050. Min Act: -0.1700
Data Index: 2474655 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.1050. Min Act: -0.1700
Data Index: 7450873 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.1050. Min Act: -0.1700
Data Index: 6569025 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3862. Min Range: -5.3862
Max Act: 5.1050. Min Act: -0.1700
Data Index: 3780590 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19