Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4374 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.6443. Min Act: -0.1700
Data Index: 8319457 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.3630. Min Act: -0.1700
Data Index: 6922414 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.3630. Min Act: -0.1700
Data Index: 1357815 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.3318. Min Act: -0.1700
Data Index: 494617 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.2693. Min Act: -0.1700
Data Index: 7430327 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.3005. Min Act: -0.1700
Data Index: 3740233 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.2380. Min Act: -0.1700
Data Index: 1832879 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.2068. Min Act: -0.1700
Data Index: 5017112 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.1755. Min Act: -0.1700
Data Index: 6135686 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.1130. Min Act: -0.1700
Data Index: 2055355 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.1755. Min Act: -0.1700
Data Index: 5259557 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.1130. Min Act: -0.1700
Data Index: 8514488 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.1443. Min Act: -0.1700
Data Index: 4993488 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.1130. Min Act: -0.1700
Data Index: 4317304 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.1443. Min Act: -0.1700
Data Index: 5489754 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.1130. Min Act: -0.1700
Data Index: 6265125 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.1130. Min Act: -0.1700
Data Index: 2714799 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.0818. Min Act: -0.1700
Data Index: 7751514 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.1130. Min Act: -0.1700
Data Index: 7847596 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6443. Min Range: -7.6443
Max Act: 7.0818. Min Act: -0.1700
Data Index: 1702443 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19