Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4027 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1195. Min Range: -10.1195
Max Act: 10.1195. Min Act: -0.1700
Data Index: 4573258 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1195. Min Range: -10.1195
Max Act: 10.0570. Min Act: -0.1700
Data Index: 7758446 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.8070. Min Act: -0.1700
Data Index: 2230493 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.6820. Min Act: -0.1700
Data Index: 2230494 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.6820. Min Act: -0.1700
Data Index: 1175225 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.6820. Min Act: -0.1700
Data Index: 8033080 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.6820. Min Act: -0.1700
Data Index: 1670239 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.6195. Min Act: -0.1700
Data Index: 7317539 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.6195. Min Act: -0.1700
Data Index: 3474985 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.5570. Min Act: -0.1700
Data Index: 2239210 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.5570. Min Act: -0.1700
Data Index: 2624880 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.5570. Min Act: -0.1700
Data Index: 8545449 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.5570. Min Act: -0.1700
Data Index: 5611103 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.5570. Min Act: -0.1700
Data Index: 102291 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.4945. Min Act: -0.1700
Data Index: 6239318 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.4320. Min Act: -0.1700
Data Index: 4308506 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.4945. Min Act: -0.1700
Data Index: 4896897 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.4945. Min Act: -0.1700
Data Index: 8152020 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.4945. Min Act: -0.1700
Data Index: 7117912 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1195. Min Range: -10.1195
Max Act: 9.4320. Min Act: -0.1700
Data Index: 1778771 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19