Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3676 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.9694. Min Act: -0.1700
Data Index: 2942047 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.9694. Min Act: -0.1700
Data Index: 4581019 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.8444. Min Act: -0.1700
Data Index: 4581015 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.6881. Min Act: -0.1700
Data Index: 4581016 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.7194. Min Act: -0.1700
Data Index: 4581017 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.5944. Min Act: -0.1700
Data Index: 937199 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.5944. Min Act: -0.1699
Data Index: 638068 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.5319. Min Act: -0.1700
Data Index: 4581018 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.5006. Min Act: -0.1700
Data Index: 2157970 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.5319. Min Act: -0.1700
Data Index: 5645963 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.4381. Min Act: -0.1700
Data Index: 8314015 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.4381. Min Act: -0.1700
Data Index: 3316704 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.4069. Min Act: -0.1700
Data Index: 2871436 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.3756. Min Act: -0.1700
Data Index: 783172 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.3756. Min Act: -0.1700
Data Index: 1595672 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.3131. Min Act: -0.1700
Data Index: 1572402 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.2506. Min Act: -0.1700
Data Index: 4745611 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.2506. Min Act: -0.1700
Data Index: 7259285 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.2506. Min Act: -0.1700
Data Index: 377265 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9694. Min Range: -4.9694
Max Act: 4.2506. Min Act: -0.1700
Data Index: 2395290 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19