Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.7732. Min Act: -0.1700
Data Index: 719847 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.7732. Min Act: -0.1700
Data Index: 5429302 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.7107. Min Act: -0.1700
Data Index: 5466458 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.7107. Min Act: -0.1700
Data Index: 2443934 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.7107. Min Act: -0.1700
Data Index: 4357270 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.6795. Min Act: -0.1700
Data Index: 4639996 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.6795. Min Act: -0.1700
Data Index: 76131 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.7107. Min Act: -0.1700
Data Index: 620083 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.6482. Min Act: -0.1700
Data Index: 3138035 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.5545. Min Act: -0.1700
Data Index: 5539906 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.5857. Min Act: -0.1700
Data Index: 5179019 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.5857. Min Act: -0.1700
Data Index: 5112217 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.5232. Min Act: -0.1700
Data Index: 1508497 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.4920. Min Act: -0.1700
Data Index: 7737187 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.4920. Min Act: -0.1700
Data Index: 7393306 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.4607. Min Act: -0.1700
Data Index: 8214623 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.4607. Min Act: -0.1700
Data Index: 923045 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.4920. Min Act: -0.1700
Data Index: 2313431 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.4295. Min Act: -0.1700
Data Index: 1754242 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7732. Min Range: -6.7732
Max Act: 6.4607. Min Act: -0.1700
Data Index: 1796632 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19