Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2612. Min Range: -7.2612
Max Act: 7.2612. Min Act: -0.1700
Data Index: 3041129 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2612. Min Range: -7.2612
Max Act: 7.2300. Min Act: -0.1700
Data Index: 3753161 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2612. Min Range: -7.2612
Max Act: 7.1675. Min Act: -0.1700
Data Index: 3741499 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2612. Min Range: -7.2612
Max Act: 7.0737. Min Act: -0.1700
Data Index: 470285 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2612. Min Range: -7.2612
Max Act: 7.0737. Min Act: -0.1700
Data Index: 3527210 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2612. Min Range: -7.2612
Max Act: 7.0425. Min Act: -0.1700
Data Index: 1165658 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2612. Min Range: -7.2612
Max Act: 7.0425. Min Act: -0.1700
Data Index: 507301 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2612. Min Range: -7.2612
Max Act: 7.0425. Min Act: -0.1700
Data Index: 1360647 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2612. Min Range: -7.2612
Max Act: 7.0112. Min Act: -0.1700
Data Index: 1309090 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2612. Min Range: -7.2612
Max Act: 7.0112. Min Act: -0.1700
Data Index: 718024 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2612. Min Range: -7.2612
Max Act: 7.0112. Min Act: -0.1700
Data Index: 416351 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2612. Min Range: -7.2612
Max Act: 7.0112. Min Act: -0.1700
Data Index: 1986756 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2612. Min Range: -7.2612
Max Act: 6.9487. Min Act: -0.1700
Data Index: 928270 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2612. Min Range: -7.2612
Max Act: 6.9800. Min Act: -0.1700
Data Index: 716963 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2612. Min Range: -7.2612
Max Act: 6.9800. Min Act: -0.1700
Data Index: 4819419 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2612. Min Range: -7.2612
Max Act: 6.9487. Min Act: -0.1700
Data Index: 5488693 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2612. Min Range: -7.2612
Max Act: 6.9487. Min Act: -0.1700
Data Index: 6687842 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2612. Min Range: -7.2612
Max Act: 6.9487. Min Act: -0.1700
Data Index: 1802224 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2612. Min Range: -7.2612
Max Act: 6.9175. Min Act: -0.1700
Data Index: 265244 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2612. Min Range: -7.2612
Max Act: 6.8862. Min Act: -0.1700
Data Index: 3342120 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19