Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 325 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.3819. Min Range: -13.3819
Max Act: 13.3819. Min Act: -0.1700
Data Index: 8529650 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.4444. Min Act: -0.1700
Data Index: 503041 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.3819. Min Act: -0.1700
Data Index: 7362317 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.2569. Min Act: -0.1700
Data Index: 5478306 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.2569. Min Act: -0.1700
Data Index: 4333468 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.2569. Min Act: -0.1700
Data Index: 2195377 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.2569. Min Act: -0.1700
Data Index: 8799412 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.1944. Min Act: -0.1700
Data Index: 7163959 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.1944. Min Act: -0.1700
Data Index: 4411927 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.1944. Min Act: -0.1700
Data Index: 8570426 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.1319. Min Act: -0.1700
Data Index: 2509436 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.1944. Min Act: -0.1700
Data Index: 1096333 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.1319. Min Act: -0.1700
Data Index: 6306949 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.1319. Min Act: -0.1700
Data Index: 879027 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.1319. Min Act: -0.1700
Data Index: 1723115 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.1319. Min Act: -0.1700
Data Index: 8424108 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.1319. Min Act: -0.1700
Data Index: 4670342 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.1319. Min Act: -0.1700
Data Index: 2032239 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.0694. Min Act: -0.1700
Data Index: 4149131 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.3819. Min Range: -13.3819
Max Act: 12.0694. Min Act: -0.1700
Data Index: 5444347 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19