Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4287. Min Range: -4.4287
Max Act: 4.4287. Min Act: -0.1700
Data Index: 2103049 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4287. Min Range: -4.4287
Max Act: 4.3662. Min Act: -0.1700
Data Index: 3753284 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4287. Min Range: -4.4287
Max Act: 4.0536. Min Act: -0.1700
Data Index: 8564107 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4287. Min Range: -4.4287
Max Act: 4.0536. Min Act: -0.1700
Data Index: 4971182 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4287. Min Range: -4.4287
Max Act: 4.0224. Min Act: -0.1700
Data Index: 6685061 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4287. Min Range: -4.4287
Max Act: 4.0536. Min Act: -0.1700
Data Index: 2790362 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4287. Min Range: -4.4287
Max Act: 4.0224. Min Act: -0.1700
Data Index: 1533081 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4287. Min Range: -4.4287
Max Act: 4.0224. Min Act: -0.1700
Data Index: 2626073 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4287. Min Range: -4.4287
Max Act: 3.9911. Min Act: -0.1700
Data Index: 734705 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4287. Min Range: -4.4287
Max Act: 3.9598. Min Act: -0.1700
Data Index: 5338578 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4287. Min Range: -4.4287
Max Act: 3.9598. Min Act: -0.1700
Data Index: 137873 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4287. Min Range: -4.4287
Max Act: 3.9598. Min Act: -0.1700
Data Index: 115695 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4287. Min Range: -4.4287
Max Act: 3.9598. Min Act: -0.1700
Data Index: 3753283 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4287. Min Range: -4.4287
Max Act: 3.9286. Min Act: -0.1700
Data Index: 2328430 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4287. Min Range: -4.4287
Max Act: 3.9286. Min Act: -0.1700
Data Index: 296026 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4287. Min Range: -4.4287
Max Act: 3.9286. Min Act: -0.1700
Data Index: 3666805 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4287. Min Range: -4.4287
Max Act: 3.9286. Min Act: -0.1700
Data Index: 5236229 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4287. Min Range: -4.4287
Max Act: 3.8973. Min Act: -0.1700
Data Index: 8564108 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4287. Min Range: -4.4287
Max Act: 3.8973. Min Act: -0.1700
Data Index: 8609830 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4287. Min Range: -4.4287
Max Act: 3.8660. Min Act: -0.1700
Data Index: 4786890 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19