Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2435 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2085. Min Range: -11.2085
Max Act: 11.2085. Min Act: -0.1700
Data Index: 3007653 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2085. Min Range: -11.2085
Max Act: 11.2085. Min Act: -0.1700
Data Index: 8173645 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2085. Min Range: -11.2085
Max Act: 11.0210. Min Act: -0.1700
Data Index: 6951400 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.9585. Min Act: -0.1700
Data Index: 689612 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.8960. Min Act: -0.1700
Data Index: 5995926 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.8960. Min Act: -0.1700
Data Index: 4857972 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.8960. Min Act: -0.1700
Data Index: 6020391 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.7710. Min Act: -0.1700
Data Index: 6288889 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.8335. Min Act: -0.1700
Data Index: 2210538 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.7710. Min Act: -0.1700
Data Index: 8441408 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.7710. Min Act: -0.1700
Data Index: 5487125 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.7710. Min Act: -0.1700
Data Index: 3759829 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.7710. Min Act: -0.1700
Data Index: 1745250 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.6460. Min Act: -0.1700
Data Index: 1000680 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.7085. Min Act: -0.1700
Data Index: 7688578 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.7085. Min Act: -0.1700
Data Index: 4255130 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.7085. Min Act: -0.1700
Data Index: 1707442 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.7085. Min Act: -0.1700
Data Index: 501305 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.7085. Min Act: -0.1700
Data Index: 6880228 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2085. Min Range: -11.2085
Max Act: 10.7085. Min Act: -0.1700
Data Index: 5773960 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19