Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1305 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.4163. Min Act: -0.1700
Data Index: 6372325 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.3538. Min Act: -0.1700
Data Index: 7546952 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.3225. Min Act: -0.1700
Data Index: 3028701 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.2600. Min Act: -0.1700
Data Index: 696141 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.2288. Min Act: -0.1700
Data Index: 4140347 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.1975. Min Act: -0.1700
Data Index: 1321474 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.1663. Min Act: -0.1700
Data Index: 5299169 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.1663. Min Act: -0.1700
Data Index: 4569392 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.1663. Min Act: -0.1700
Data Index: 8401348 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.1350. Min Act: -0.1700
Data Index: 5020976 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.1350. Min Act: -0.1700
Data Index: 422775 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.1350. Min Act: -0.1700
Data Index: 5019228 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.1350. Min Act: -0.1700
Data Index: 1040731 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.1350. Min Act: -0.1700
Data Index: 2335634 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.1038. Min Act: -0.1700
Data Index: 5947071 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.1350. Min Act: -0.1700
Data Index: 2795314 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.0725. Min Act: -0.1700
Data Index: 1512976 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.0413. Min Act: -0.1700
Data Index: 7816024 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.0413. Min Act: -0.1700
Data Index: 4161458 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4163. Min Range: -5.4163
Max Act: 5.0100. Min Act: -0.1700
Data Index: 5819332 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19