Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2849 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6443. Min Range: -6.6443
Max Act: 6.6443. Min Act: -0.1700
Data Index: 1657652 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6443. Min Range: -6.6443
Max Act: 6.4255. Min Act: -0.1700
Data Index: 4503948 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6443. Min Range: -6.6443
Max Act: 6.3005. Min Act: -0.1700
Data Index: 7146859 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6443. Min Range: -6.6443
Max Act: 6.1755. Min Act: -0.1700
Data Index: 8558803 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6443. Min Range: -6.6443
Max Act: 6.1443. Min Act: -0.1700
Data Index: 537281 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6443. Min Range: -6.6443
Max Act: 6.1130. Min Act: -0.1700
Data Index: 5172677 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6443. Min Range: -6.6443
Max Act: 6.0818. Min Act: -0.1700
Data Index: 8574332 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6443. Min Range: -6.6443
Max Act: 6.0818. Min Act: -0.1700
Data Index: 1946841 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6443. Min Range: -6.6443
Max Act: 6.0505. Min Act: -0.1700
Data Index: 227270 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6443. Min Range: -6.6443
Max Act: 6.0505. Min Act: -0.1700
Data Index: 2750128 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6443. Min Range: -6.6443
Max Act: 6.0505. Min Act: -0.1700
Data Index: 7298860 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6443. Min Range: -6.6443
Max Act: 6.0818. Min Act: -0.1700
Data Index: 1784796 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6443. Min Range: -6.6443
Max Act: 5.9880. Min Act: -0.1700
Data Index: 5942799 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6443. Min Range: -6.6443
Max Act: 5.8943. Min Act: -0.1700
Data Index: 8332882 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6443. Min Range: -6.6443
Max Act: 5.8943. Min Act: -0.1700
Data Index: 704192 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6443. Min Range: -6.6443
Max Act: 5.8318. Min Act: -0.1700
Data Index: 6153511 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6443. Min Range: -6.6443
Max Act: 5.8005. Min Act: -0.1700
Data Index: 3954865 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6443. Min Range: -6.6443
Max Act: 5.8318. Min Act: -0.1700
Data Index: 8383298 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6443. Min Range: -6.6443
Max Act: 5.8005. Min Act: -0.1700
Data Index: 1653257 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6443. Min Range: -6.6443
Max Act: 5.8318. Min Act: -0.1700
Data Index: 926444 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19