Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5222 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.7345. Min Act: -0.1700
Data Index: 2318283 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.6095. Min Act: -0.1700
Data Index: 5179878 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.5470. Min Act: -0.1700
Data Index: 5028966 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.4220. Min Act: -0.1700
Data Index: 8258283 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.3908. Min Act: -0.1700
Data Index: 5368968 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.3908. Min Act: -0.1700
Data Index: 7442679 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.3283. Min Act: -0.1700
Data Index: 7586957 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.2658. Min Act: -0.1700
Data Index: 2156988 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.2033. Min Act: -0.1700
Data Index: 4168215 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.2033. Min Act: -0.1700
Data Index: 399748 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.1095. Min Act: -0.1700
Data Index: 7874420 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.1095. Min Act: -0.1700
Data Index: 896241 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.1408. Min Act: -0.1700
Data Index: 388312 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.0783. Min Act: -0.1700
Data Index: 5964240 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.0470. Min Act: -0.1700
Data Index: 5112449 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.0470. Min Act: -0.1700
Data Index: 2088280 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.0158. Min Act: -0.1700
Data Index: 3559381 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.0158. Min Act: -0.1700
Data Index: 6821221 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.0158. Min Act: -0.1700
Data Index: 2191569 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7345. Min Range: -5.7345
Max Act: 5.0158. Min Act: -0.1700
Data Index: 2861350 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19