Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4612 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.4600. Min Act: -0.1700
Data Index: 7605654 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.3663. Min Act: -0.1700
Data Index: 4172798 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.3038. Min Act: -0.1700
Data Index: 1439604 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.2725. Min Act: -0.1700
Data Index: 1956397 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.2725. Min Act: -0.1700
Data Index: 1484110 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.1788. Min Act: -0.1700
Data Index: 8533502 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.1788. Min Act: -0.1700
Data Index: 5491219 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.1788. Min Act: -0.1700
Data Index: 2755972 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.1788. Min Act: -0.1700
Data Index: 3313422 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.1163. Min Act: -0.1700
Data Index: 1309019 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.1475. Min Act: -0.1700
Data Index: 4638051 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.1475. Min Act: -0.1700
Data Index: 6218682 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.1163. Min Act: -0.1700
Data Index: 3523906 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.1163. Min Act: -0.1700
Data Index: 4200209 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.1163. Min Act: -0.1700
Data Index: 5959717 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.1163. Min Act: -0.1700
Data Index: 3509834 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.0850. Min Act: -0.1700
Data Index: 5413613 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.0850. Min Act: -0.1700
Data Index: 4706433 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.0850. Min Act: -0.1700
Data Index: 3535674 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4600. Min Range: -5.4600
Max Act: 5.0850. Min Act: -0.1700
Data Index: 6603046 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19