Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3154 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.7287. Min Act: -0.1700
Data Index: 853606 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.6974. Min Act: -0.1700
Data Index: 2351944 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.3224. Min Act: -0.1700
Data Index: 6562886 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.2912. Min Act: -0.1700
Data Index: 1169913 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.2912. Min Act: -0.1700
Data Index: 3081091 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.2912. Min Act: -0.1700
Data Index: 6458618 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.2599. Min Act: -0.1700
Data Index: 8035719 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.2599. Min Act: -0.1700
Data Index: 417796 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.2599. Min Act: -0.1700
Data Index: 3977755 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.2287. Min Act: -0.1700
Data Index: 2792163 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.2287. Min Act: -0.1700
Data Index: 1740514 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.1974. Min Act: -0.1700
Data Index: 8754532 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.1974. Min Act: -0.1700
Data Index: 4457843 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.1662. Min Act: -0.1700
Data Index: 8832893 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.1974. Min Act: -0.1700
Data Index: 2962271 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.1974. Min Act: -0.1700
Data Index: 8746048 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.1662. Min Act: -0.1700
Data Index: 4410099 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.1662. Min Act: -0.1700
Data Index: 1476489 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.1349. Min Act: -0.1700
Data Index: 6338883 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.1349. Min Act: -0.1700
Data Index: 2968058 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19