Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 418 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.7712. Min Act: -0.1700
Data Index: 3100603 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.7712. Min Act: -0.1700
Data Index: 2209551 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.7399. Min Act: -0.1700
Data Index: 5443830 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.7399. Min Act: -0.1700
Data Index: 5516141 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.7087. Min Act: -0.1700
Data Index: 5165847 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.6774. Min Act: -0.1700
Data Index: 4695170 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.6462. Min Act: -0.1700
Data Index: 8385949 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.6462. Min Act: -0.1700
Data Index: 6652802 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.6774. Min Act: -0.1700
Data Index: 3665077 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.6774. Min Act: -0.1700
Data Index: 2525829 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.6462. Min Act: -0.1700
Data Index: 7762741 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.6149. Min Act: -0.1700
Data Index: 520607 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.6149. Min Act: -0.1700
Data Index: 1409606 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.6462. Min Act: -0.1700
Data Index: 1299814 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.6149. Min Act: -0.1700
Data Index: 3847248 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.6149. Min Act: -0.1700
Data Index: 330688 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.6149. Min Act: -0.1700
Data Index: 4407831 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.5837. Min Act: -0.1700
Data Index: 7099184 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.6149. Min Act: -0.1700
Data Index: 7551503 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7712. Min Range: -4.7712
Max Act: 4.6149. Min Act: -0.1700
Data Index: 5761908 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19