Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1225 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2932. Min Range: -8.2932
Max Act: 8.2932. Min Act: -0.1700
Data Index: 2204179 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2932. Min Range: -8.2932
Max Act: 8.0432. Min Act: -0.1700
Data Index: 7353761 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2932. Min Range: -8.2932
Max Act: 8.0744. Min Act: -0.1700
Data Index: 56618 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.9807. Min Act: -0.1700
Data Index: 3763424 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.9807. Min Act: -0.1700
Data Index: 8591816 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.9494. Min Act: -0.1700
Data Index: 4128762 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.9807. Min Act: -0.1700
Data Index: 401932 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.8869. Min Act: -0.1700
Data Index: 1564557 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.8557. Min Act: -0.1700
Data Index: 7414707 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.8557. Min Act: -0.1700
Data Index: 8043125 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.8244. Min Act: -0.1700
Data Index: 5397502 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.8244. Min Act: -0.1700
Data Index: 126851 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.8244. Min Act: -0.1700
Data Index: 8256774 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.7307. Min Act: -0.1700
Data Index: 6735268 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.7619. Min Act: -0.1700
Data Index: 7062869 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.6994. Min Act: -0.1700
Data Index: 2841023 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.7307. Min Act: -0.1700
Data Index: 2822680 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.6682. Min Act: -0.1700
Data Index: 7618933 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.6682. Min Act: -0.1700
Data Index: 5397495 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2932. Min Range: -8.2932
Max Act: 7.6369. Min Act: -0.1700
Data Index: 6399932 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19