Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2304 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0576. Min Range: -7.0576
Max Act: 7.0576. Min Act: -0.1700
Data Index: 7241284 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.8388. Min Act: -0.1700
Data Index: 4361924 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.7451. Min Act: -0.1700
Data Index: 2307512 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.7451. Min Act: -0.1700
Data Index: 8252709 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.7138. Min Act: -0.1700
Data Index: 7646931 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.6513. Min Act: -0.1700
Data Index: 3723027 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.6513. Min Act: -0.1700
Data Index: 2683460 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.6201. Min Act: -0.1700
Data Index: 1643562 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.5888. Min Act: -0.1700
Data Index: 6648856 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.5263. Min Act: -0.1700
Data Index: 75766 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.4951. Min Act: -0.1700
Data Index: 8798373 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.4638. Min Act: -0.1700
Data Index: 3744087 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.4638. Min Act: -0.1700
Data Index: 2063067 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.4638. Min Act: -0.1700
Data Index: 433096 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.4638. Min Act: -0.1700
Data Index: 7062627 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.4326. Min Act: -0.1700
Data Index: 8112638 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.4326. Min Act: -0.1700
Data Index: 6647251 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.4326. Min Act: -0.1700
Data Index: 4827175 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.4326. Min Act: -0.1700
Data Index: 8507187 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0576. Min Range: -7.0576
Max Act: 6.4638. Min Act: -0.1700
Data Index: 575317 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19