Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2882. Min Range: -7.2882
Max Act: 7.2882. Min Act: -0.1700
Data Index: 414379 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.9445. Min Act: -0.1700
Data Index: 8569564 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.8507. Min Act: -0.1700
Data Index: 1866494 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.8195. Min Act: -0.1700
Data Index: 7904058 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.8195. Min Act: -0.1700
Data Index: 1121791 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.7882. Min Act: -0.1700
Data Index: 6936458 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.7882. Min Act: -0.1700
Data Index: 1801271 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.7570. Min Act: -0.1700
Data Index: 4463859 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.7257. Min Act: -0.1700
Data Index: 5741470 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.7257. Min Act: -0.1700
Data Index: 5511553 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.6632. Min Act: -0.1700
Data Index: 2309725 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.6945. Min Act: -0.1700
Data Index: 2301256 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.6945. Min Act: -0.1700
Data Index: 3308459 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.6632. Min Act: -0.1700
Data Index: 1987682 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.6632. Min Act: -0.1700
Data Index: 552215 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.6632. Min Act: -0.1700
Data Index: 2994515 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.6632. Min Act: -0.1700
Data Index: 8425903 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.6632. Min Act: -0.1700
Data Index: 7629487 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.6320. Min Act: -0.1700
Data Index: 59851 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2882. Min Range: -7.2882
Max Act: 6.6007. Min Act: -0.1700
Data Index: 8609288 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19