Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1960 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4395. Min Range: -8.4395
Max Act: 8.4395. Min Act: -0.1700
Data Index: 6947160 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4395. Min Range: -8.4395
Max Act: 8.0645. Min Act: -0.1700
Data Index: 5371908 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4395. Min Range: -8.4395
Max Act: 8.0645. Min Act: -0.1700
Data Index: 5298656 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.9707. Min Act: -0.1700
Data Index: 3545116 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.9395. Min Act: -0.1700
Data Index: 8593563 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.9082. Min Act: -0.1700
Data Index: 8536145 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.8770. Min Act: -0.1700
Data Index: 62859 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.8457. Min Act: -0.1700
Data Index: 5718528 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.8145. Min Act: -0.1700
Data Index: 5049244 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.7832. Min Act: -0.1700
Data Index: 7321772 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.7832. Min Act: -0.1700
Data Index: 5572513 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.7832. Min Act: -0.1700
Data Index: 931073 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.7832. Min Act: -0.1700
Data Index: 494048 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.7520. Min Act: -0.1700
Data Index: 4005882 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.7207. Min Act: -0.1700
Data Index: 3833331 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.7207. Min Act: -0.1700
Data Index: 8519961 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.6895. Min Act: -0.1700
Data Index: 905574 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.6895. Min Act: -0.1700
Data Index: 1716444 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.6895. Min Act: -0.1700
Data Index: 2065673 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4395. Min Range: -8.4395
Max Act: 7.7207. Min Act: -0.1700
Data Index: 7452129 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19